{
"cells": [
{
"cell_type": "markdown",
"id": "42a52629",
"metadata": {
"id": "colab-badge",
"papermill": {
"duration": 0.004462,
"end_time": "2026-07-31T21:35:05.947968+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:05.943506+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"\n",
"
\n",
""
]
},
{
"cell_type": "markdown",
"id": "7fb27b941602401d91542211134fc71a",
"metadata": {
"papermill": {
"duration": 0.003557,
"end_time": "2026-07-31T21:35:05.968339+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:05.964782+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"# Concept-Direction Steering Demo (local Neuronpedia)\n",
"\n",
"Demonstrates interpretune's **concept-direction-mediated, sign-aware, multi-feature steering** on a\n",
"trivial example, `orange` color-vs-fruit sense disambiguation to familiarize the user with some of interpretune's\n",
"intervention mechanisms:\n",
"\n",
"1. **Feature-mediated path**: concept direction -> attribution graph -> sign-aware\n",
" `FeatureSelectionSpec` top-feature selection -> `feature_intervention_forward` (circuit-tracer\n",
" feature interventions with sign-aware, influence-normalized scaling).\n",
"2. **Direct-hook path**: the same concept direction applied via `model_fwd_intervention`\n",
" (hook-tensor add/project interventions at canonical hook points).\n",
"\n",
"Both paths derive the concept direction from the token-embedding basis (`paired_rejection`\n",
"over the concept groups).\n",
"\n",
"The `BACKEND` parameter selects the circuit-tracer backend for all steps: NNsight (default)\n",
"or TransformerLens — both are validated by the parameterized notebook tests. (The\n",
"TransformerLens backend uses the legacy `HookedTransformer` path; circuit-tracer does not yet\n",
"support `TransformerBridge` — see the tracking notes in `docs/circuit_tracer_backend_support.md`.)\n",
"\n",
"This is the local-Neuronpedia variant: it runs the instruction-tuned `gemma-3-1b-it`\n",
"substrate against a local Neuronpedia dev webapp + database, and resolves feature explanations\n",
"from that local database (optionally generating any that are missing). It exercises the full local\n",
"pipeline — dashboards -> explanations -> selection -> steering.\n",
"\n",
"For the zero-setup version that uses the public [neuronpedia.org](https://www.neuronpedia.org)\n",
"dashboards and needs no local services, see\n",
"[`ct_concept_steering_demo.ipynb`](ct_concept_steering_demo.ipynb).\n",
"\n",
"> **Prerequisites**: a GPU with bf16 support, the model/transcoder weights, and a running local\n",
"> Neuronpedia webapp + Postgres serving the `gemmascope-2-transcoder-16k` dashboards for\n",
"> `gemma-3-1b-it` (see `docs/neuronpedia_dashboard_pipeline.md`). Explanation *generation* is\n",
"> optional and additionally needs the explanation CLI + an API key — see the next cell.\n",
"\n",
"> **Expected result — the three steering paths are not equally strong.** The attribution-graph\n",
"> feature-mediated path (step 2) is the one selecting features *for their causal effect on the target\n",
"> logit difference*, and it should produce the largest target-gap shift. Direct-hook steering (step 4)\n",
"> applies a concept direction at a hook point without that per-feature attribution, and the optional\n",
"> user-curated path (step 5) picks features by human dashboard inspection — features chosen for what\n",
"> they *fire on* rather than what they *write to*. Both are expected to be **weaker** than the\n",
"> attribution-mediated result. That gap is a finding, not a defect: step 6's decoupling analysis\n",
"> exists to explain it, showing curated picks typically carry high input-concept share but the\n",
"> smallest |output projections|.\n"
]
},
{
"cell_type": "markdown",
"id": "acae54e37e7d407bbb7b55eff062a284",
"metadata": {
"id": "explanation-env-setup",
"papermill": {
"duration": 0.00387,
"end_time": "2026-07-31T21:35:05.975838+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:05.971968+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"### Credentials for local explanation generation (optional)\n",
"\n",
"Only needed when `GENERATE_MISSING_LOCAL_EXPLANATIONS=True` (or `REGENERATE_LOCAL_EXPLANATIONS=True`).\n",
"Everything else in this notebook runs without it — explanations already present in the local\n",
"database are read directly.\n",
"\n",
"Generation shells out to a conforming CLI (GitHub Copilot by default). Set these **before**\n",
"starting the kernel, e.g. in the repo `.env` or your shell:\n",
"\n",
"```bash\n",
"export IT_EXPLANATION_PROVIDER_API_KEY=sk-or-v1-... # an OpenRouter key works here\n",
"export IT_EXPLANATION_CLI_MODEL=nvidia/nemotron-3-ultra-550b-a55b:free\n",
"```\n",
"\n",
"Key precedence, highest first: `IT_EXPLANATION_PROVIDER_API_KEY` -> `COPILOT_PROVIDER_API_KEY`\n",
"-> `OPENROUTER_API_KEY`. The endpoint follows the **key**, not the variable holding it, so an\n",
"OpenRouter key (`sk-or-` prefix) routes to OpenRouter from any of them. Always set\n",
"`IT_EXPLANATION_CLI_MODEL` with an OpenRouter key -- the default model id belongs to another\n",
"provider and will not resolve.\n",
"\n",
"Set `REGENERATE_LOCAL_EXPLANATIONS=True` to re-generate features that already have an\n",
"explanation. On an already-populated database every feature is otherwise skipped, so the run\n",
"reports full coverage without the CLI being called once. Nothing is deleted.\n"
]
},
{
"cell_type": "code",
"execution_count": 2,
"id": "9a63283cbaf04dbcab1f6479b197f3a8",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:35:05.984425Z",
"iopub.status.busy": "2026-07-31T21:35:05.984275Z",
"iopub.status.idle": "2026-07-31T21:35:05.990979Z",
"shell.execute_reply": "2026-07-31T21:35:05.990062Z"
},
"papermill": {
"duration": 0.012214,
"end_time": "2026-07-31T21:35:05.991681+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:05.979467+00:00",
"status": "completed"
},
"tags": [
"parameters"
]
},
"outputs": [],
"source": [
"# Parameters - These will be injected by papermill during parameterized test runs\n",
"BACKEND = \"nnsight\" # circuit-tracer backend for all steps: \"nnsight\" or \"transformerlens\"\n",
"CONCEPT_PROMPT = \"Is orange a color or a fruit? Answer with one word: Color or Fruit. orange ->\"\n",
"CONCEPT_TARGET_TOKENS = [\"Fruit\", \"Color\"]\n",
"FEATURE_SELECTION_TOP_N = 5\n",
"FEATURE_SELECTION_MIN_LAYER = 10 # fs_l10_n5 lineage: layers >= 10\n",
"FEATURE_SELECTION_SCORE_SIGN = \"any\" # any | positive | negative\n",
"INTERVENTION_SCALE_FACTOR = 20.0 # validated s5_any demo scale\n",
"EMBED_INTERVENTION_MODE = \"add\" # model_fwd_intervention mode for the embed step\n",
"EMBED_INTERVENTION_HOOK = \"unembed.hook_in\"\n",
"\n",
"# -- Model / dashboard substrate: gemma-3-1b-it + a LOCAL Neuronpedia dev webapp ----------------\n",
"# Dashboard/runtime width must match: the served source set has to correspond to the runtime\n",
"# transcoder_set width. Feature indices are only meaningful within one feature space.\n",
"REGISTRY_KEY = \"gemma3.rte_demo.circuit_tracer_w_neuronpedia\"\n",
"MODEL_NAME = \"gemma-3-1b-it\"\n",
"TRANSCODER_SET = None # keep the registry default (gemma-scope-2, 16k width)\n",
"NEURONPEDIA_MODEL_ID = \"gemma-3-1b-it\"\n",
"NEURONPEDIA_SOURCE_SET = \"gemmascope-2-transcoder-16k\" # matches the registry transcoder width (16k)\n",
"CHAT_FORMAT_PROMPT = True # gemma-3-1b-it is instruction-tuned\n",
"LOCAL_WEBAPP_URL = \"http://localhost:3000\"\n",
"LOCAL_DB_URL = \"postgres://postgres:postgres@127.0.0.1:5433/postgres\"\n",
"\n",
"# -- Local explanation generation (OPTIONAL) ----------------------------------------------------\n",
"# Everything above runs without these. Generation shells out to a conforming CLI and needs an API\n",
"# key -- see the credentials cell below.\n",
"GENERATE_MISSING_LOCAL_EXPLANATIONS = False # backfill features that have no local explanation yet\n",
"REGENERATE_LOCAL_EXPLANATIONS = False # also re-generate features that already have one\n",
"\n",
"# -- Step 5 (user-curated feature steering) -- DISABLED BY DEFAULT ------------------------------\n",
"# Curated steering pins specific (layer, feature) ids that were found by manual dashboard search\n",
"# against one dashboard generation. Curated ids are tied to a specific (model, source set) pair --\n",
"# they index the transcoder's feature space, so they stay valid across regenerations of the SAME\n",
"# model/source set, but they do not carry across models, widths or source sets. The *explanations*\n",
"# that justified picking them are weaker: those describe the dashboard evidence, which does change\n",
"# when the corpus changes. Sharing curated picks reliably needs a shared dashboard artifact, which is\n",
"# not available yet (priority item on the IT roadmap).\n",
"#\n",
"# So it is OFF unless you supply ids for YOUR dashboards. To enable, fill in the two lists below with\n",
"# features you located in your own local webapp.\n",
"#\n",
"# This becomes a safe default once the generated dashboard artifacts are downloadable from the Hub,\n",
"# because then everyone can share one substrate with stable ids -- tracked for the IT MVP milestone.\n",
"CURATED_FEATURES_SOURCE_SET = \"gemmascope-2-transcoder-16k\"\n",
"CURATED_POSITIVE_FEATURES: list[tuple[int, int]] = [] # amplify; e.g. [(19, 11234)] on our 24,576-prompt 16k set\n",
"CURATED_NEGATIVE_FEATURES: list[tuple[int, int]] = [] # suppress; e.g. [(16, 199), (16, 13701), (17, 6499)]\n",
"CURATED_OVERRIDE_MAGNITUDE = 4.0 # fixed |activation| override per curated feature"
]
},
{
"cell_type": "code",
"execution_count": 4,
"id": "8dd0d8092fe74a7c96281538738b07e2",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:35:06.013745Z",
"iopub.status.busy": "2026-07-31T21:35:06.013548Z",
"iopub.status.idle": "2026-07-31T21:35:18.014968Z",
"shell.execute_reply": "2026-07-31T21:35:18.014096Z"
},
"papermill": {
"duration": 12.007398,
"end_time": "2026-07-31T21:35:18.016189+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:06.008791+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [],
"source": [
"# @title Imports { display-mode: \"form\" }\n",
"import torch # noqa: F401\n",
"\n",
"import interpretune.analysis # noqa: F401 # ensure op wrappers are registered\n",
"from interpretune.analysis.backends import FeatureSelectionSpec # noqa: F401\n",
"from interpretune.utils import ensure_local_feature_explanations, feature_tuples_to_feature_refs # noqa: F401\n",
"from it_examples.utils.nb_ui_utils import ( # noqa: F401\n",
" best_variant_token_ids,\n",
" display_steering_results,\n",
" display_target_gap,\n",
" display_top_features_comparison,\n",
" resolve_feature_explanations,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "72eea5119410473aa328ad9291626812",
"metadata": {
"papermill": {
"duration": 0.003793,
"end_time": "2026-07-31T21:35:18.024225+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:18.020432+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## 1. Session setup\n",
"\n",
"Single-backend circuit-tracer session built from the `REGISTRY_KEY` example-registry entry."
]
},
{
"cell_type": "code",
"execution_count": 5,
"id": "8edb47106e1a46a883d545849b8ab81b",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:35:18.033009Z",
"iopub.status.busy": "2026-07-31T21:35:18.032866Z",
"iopub.status.idle": "2026-07-31T21:35:45.584534Z",
"shell.execute_reply": "2026-07-31T21:35:45.583603Z"
},
"papermill": {
"duration": 27.557743,
"end_time": "2026-07-31T21:35:45.585749+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:18.028006+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.extensions.neuronpedia: Neuronpedia package available\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.extensions.neuronpedia:Neuronpedia package available\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Loading ReplacementModel with backend: nnsight\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Loading ReplacementModel with backend: nnsight\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "fa492f0c13ae440db7ef0da54ef80b6f",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Downloading (incomplete total...): 0.00B [00:00, ?B/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "74b15a0f47464ba891687402fca75397",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Fetching 26 files: 0%| | 0/26 [00:00, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "da8aa869221b47b7ae79ad8509ad14d7",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Loading weights: 0%| | 0/340 [00:00, ?it/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: NNsight ReplacementModel initialized for Circuit Tracer\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:NNsight ReplacementModel initialized for Circuit Tracer\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Attempted to clean a key that was not present, continuing without cleaning that key: 'Gemma3TextConfig' object has no attribute 'quantization_config'\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Attempted to clean a key that was not present, continuing without cleaning that key: 'Gemma3TextConfig' object has no attribute 'quantization_config'\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Attempted to clean a key that was not present, continuing without cleaning that key: 'Gemma3TextConfig' object has no attribute '_pre_quantization_dtype'\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Attempted to clean a key that was not present, continuing without cleaning that key: 'Gemma3TextConfig' object has no attribute '_pre_quantization_dtype'\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Preparing data: InterpretunableDataModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Preparing data: InterpretunableDataModule\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6a41b86b85634277a7384f40774fcdb2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/2490 [00:00, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: The following columns don't have a corresponding argument in `NNSightReplacementModel.forward` and have been ignored: hypothesis, idx, label, premise, sequences. If hypothesis, idx, label, premise, sequences are not expected by `NNSightReplacementModel.forward`, you can safely ignore this message.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:The following columns don't have a corresponding argument in `NNSightReplacementModel.forward` and have been ignored: hypothesis, idx, label, premise, sequences. If hypothesis, idx, label, premise, sequences are not expected by `NNSightReplacementModel.forward`, you can safely ignore this message.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "7da3eb95aada4a25b5906539cc6b9315",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/277 [00:00, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: The following columns don't have a corresponding argument in `NNSightReplacementModel.forward` and have been ignored: hypothesis, idx, label, premise, sequences. If hypothesis, idx, label, premise, sequences are not expected by `NNSightReplacementModel.forward`, you can safely ignore this message.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:The following columns don't have a corresponding argument in `NNSightReplacementModel.forward` and have been ignored: hypothesis, idx, label, premise, sequences. If hypothesis, idx, label, premise, sequences are not expected by `NNSightReplacementModel.forward`, you can safely ignore this message.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "461cea9cb47545e9863e34a1cfebe2b9",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Map: 0%| | 0/3000 [00:00, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: The following columns don't have a corresponding argument in `NNSightReplacementModel.forward` and have been ignored: hypothesis, idx, label, premise, sequences. If hypothesis, idx, label, premise, sequences are not expected by `NNSightReplacementModel.forward`, you can safely ignore this message.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:The following columns don't have a corresponding argument in `NNSightReplacementModel.forward` and have been ignored: hypothesis, idx, label, premise, sequences. If hypothesis, idx, label, premise, sequences are not expected by `NNSightReplacementModel.forward`, you can safely ignore this message.\n"
]
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "6cb91a8925674514a5e59227276af2a2",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Saving the dataset (0/1 shards): 0%| | 0/2490 [00:00, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "1d79881ce6614a58bcb9ce58b6acaff0",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Saving the dataset (0/1 shards): 0%| | 0/277 [00:00, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"application/vnd.jupyter.widget-view+json": {
"model_id": "2fa89b71d0014dd9a3d027f7ecd25403",
"version_major": 2,
"version_minor": 0
},
"text/plain": [
"Saving the dataset (0/1 shards): 0%| | 0/3000 [00:00, ? examples/s]"
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Setting up datamodule: InterpretunableDataModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Setting up datamodule: InterpretunableDataModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Setting up model: InterpretunableModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Setting up model: InterpretunableModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: initializing optimizers and schedulers: InterpretunableModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:initializing optimizers and schedulers: InterpretunableModule\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"[INFO] interpretune.utils.logging: Input gradient requirements handled by circuit tracer internally.\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"INFO:interpretune.utils.logging:Input gradient requirements handled by circuit tracer internally.\n"
]
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"session ready: InterpretunableModule (gemma-3-1b-it + circuit-tracer nnsight backend)\n"
]
}
],
"source": [
"# @title 1: Session construction { display-mode: \"form\" }\n",
"from pathlib import Path\n",
"\n",
"from dotenv import load_dotenv\n",
"\n",
"import interpretune as it\n",
"from it_examples import _ACTIVE_PATCHES # noqa: F401 # runtime analysis-hook patches\n",
"from it_examples.example_module_registry import MODULE_EXAMPLE_REGISTRY\n",
"from interpretune import ITSession, ITSessionConfig\n",
"\n",
"# load HF credentials before session init (model + transcoder downloads)\n",
"for _env_candidate in (Path.cwd() / \".env\", Path.home() / \"repos\" / \"interpretune\" / \".env\"):\n",
" if _env_candidate.exists():\n",
" load_dotenv(_env_candidate)\n",
" break\n",
"\n",
"base_itdm_cfg, base_it_cfg, dm_cls, m_cls = MODULE_EXAMPLE_REGISTRY.get(REGISTRY_KEY)\n",
"# single circuit-tracer backend for all phases (BACKEND selects the replacement-model implementation)\n",
"base_it_cfg.circuit_tracer_cfg.backend = BACKEND\n",
"if TRANSCODER_SET:\n",
" base_it_cfg.circuit_tracer_cfg.transcoder_set = TRANSCODER_SET\n",
"if BACKEND == \"nnsight\":\n",
" adapter_ctx = (it.Adapter.core, it.Adapter.nnsight, it.Adapter.circuit_tracer)\n",
"else:\n",
" # the TL circuit-tracer backend needs the transformer_lens adapter in the composition\n",
" # (it provides the replacement-model init path; see docs/circuit_tracer_backend_support.md)\n",
" adapter_ctx = (it.Adapter.core, it.Adapter.transformer_lens, it.Adapter.circuit_tracer)\n",
"session_cfg = ITSessionConfig(\n",
" adapter_ctx=adapter_ctx,\n",
" datamodule_cfg=base_itdm_cfg,\n",
" module_cfg=base_it_cfg,\n",
" datamodule_cls=dm_cls,\n",
" module_cls=m_cls,\n",
")\n",
"it_session = ITSession(session_cfg)\n",
"it.it_init(**it_session)\n",
"module = it_session.module\n",
"tokenizer = module.replacement_model.tokenizer\n",
"print(f\"session ready: {type(module).__name__} ({MODEL_NAME} + circuit-tracer {BACKEND} backend)\")"
]
},
{
"cell_type": "markdown",
"id": "10185d26023b46108eb7d9f57d49d2b3",
"metadata": {
"papermill": {
"duration": 0.006564,
"end_time": "2026-07-31T21:35:45.599255+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:45.592691+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## 2. Feature-mediated path: concept direction -> attribution -> sign-aware selection -> feature steering\n",
"\n",
"Runs the registered composite `it.intervention_from_concept(...)` (concept_direction ->\n",
"compute_attribution_graph -> graph_node_influence -> extract_top_features ->\n",
"feature_intervention_forward) with:\n",
"\n",
"- `FeatureSelectionSpec(layer_slice=(FEATURE_SELECTION_MIN_LAYER, None), score_sign=FEATURE_SELECTION_SCORE_SIGN,\n",
" score_source=\"signed_influence\")`\n",
"- sign-aware, influence-normalized scaling\n",
" (`intervention_sign_aware_scale=True`, `intervention_max_influence_norm_scale=True`,\n",
" `intervention_value_source=\"top_feature_activation_values\"`, `intervention_scale_factor=INTERVENTION_SCALE_FACTOR`)\n",
"\n",
"Expected outcome: post-intervention target gap exceeds the pre-intervention gap and the\n",
"post-intervention argmax lands in the target-token variant set.\n"
]
},
{
"cell_type": "code",
"execution_count": 6,
"id": "8763a12b2bbd4a93a75aff182afb95dc",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:35:45.613712Z",
"iopub.status.busy": "2026-07-31T21:35:45.613518Z",
"iopub.status.idle": "2026-07-31T21:35:57.422909Z",
"shell.execute_reply": "2026-07-31T21:35:57.421793Z"
},
"papermill": {
"duration": 11.817935,
"end_time": "2026-07-31T21:35:57.423641+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:45.605706+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stderr",
"output_type": "stream",
"text": [
"Phase 0: Precomputing activations and vectors\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Precomputation completed in 1.07s\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Found 11630 active features\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Phase 1: Running forward pass\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/mnt/cache/speediedan/.venvs/it_latest/lib/python3.13/site-packages/circuit_tracer/transcoder/single_layer_transcoder.py:139: UserWarning: Attempting to run cuBLAS, but there was no current CUDA context! Attempting to set the primary context... (Triggered internally at /__w/pytorch/pytorch/aten/src/ATen/cuda/CublasHandlePool.cpp:408.)\n",
" return input_acts @ self.W_skip.T\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Forward pass completed in 0.70s\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Phase 2: Building input vectors\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Using 1 custom attribution targets with total weight 0.0000\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Will include 8192 of 11630 feature nodes\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Input vectors built in 0.44s\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Phase 3: Computing logit attributions\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"1 logit attribution(s) completed in 0.11s\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Phase 4: Computing feature attributions\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 0%| | 0/8192 [00:00, ?it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 3%|▎ | 256/8192 [00:00<00:07, 1132.24it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 9%|▉ | 768/8192 [00:00<00:03, 2183.49it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 16%|█▌ | 1280/8192 [00:00<00:02, 2458.82it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 22%|██▏ | 1792/8192 [00:00<00:02, 2666.47it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 28%|██▊ | 2304/8192 [00:00<00:02, 2820.03it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 34%|███▍ | 2816/8192 [00:01<00:01, 2914.13it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 41%|████ | 3328/8192 [00:01<00:01, 2927.18it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 47%|████▋ | 3840/8192 [00:01<00:01, 2957.87it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 53%|█████▎ | 4352/8192 [00:01<00:01, 2838.65it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 59%|█████▉ | 4864/8192 [00:01<00:01, 2922.40it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 66%|██████▌ | 5376/8192 [00:01<00:01, 2779.26it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 72%|███████▏ | 5888/8192 [00:02<00:00, 2881.31it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 78%|███████▊ | 6400/8192 [00:02<00:00, 2702.29it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 84%|████████▍ | 6912/8192 [00:02<00:00, 2815.04it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 91%|█████████ | 7424/8192 [00:02<00:00, 2671.61it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 97%|█████████▋| 7936/8192 [00:02<00:00, 2788.91it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\r",
"Feature influence computation: 100%|██████████| 8192/8192 [00:02<00:00, 2748.10it/s]"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"\n",
"Feature attributions completed in 2.98s\n"
]
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"Attribution completed in 6.39s\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
"
| # | Node | Sign | |Score| |
|---|
| 1 | (25, 27, 1316) | − | 2.55e-08 |
| 2 | (25, 27, 765) | − | 1.74e-08 |
| 3 | (16, 27, 155) | + | 1.04e-08 |
| 4 | (23, 27, 725) | − | 6.98e-09 |
| 5 | (25, 27, 662) | − | 6.41e-09 |
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
" \n",
"
Feature-mediated steering — target gap
\n",
"
\n",
" \n",
" \n",
" | Token | \n",
" Pre prob | \n",
" Post prob | \n",
" Pre logit | \n",
" Post logit | \n",
" Δ | \n",
"
\n",
" \n",
" \n",
" | Fruit | 4.31e-04 | 2.26e-06 | 41.5000 | 79.5000 | +38.0000 |
\n",
"| Color | 99.957% | 5.82e-24 | 49.2500 | 39.0000 | -10.2500 |
\n",
"| Gap (Fruit − Color) | | | -7.7500 | +40.5000 | +48.2500 |
\n",
"\n",
" \n",
"
\n",
"
\n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# @title 2: Feature-mediated steering { display-mode: \"form\" }\n",
"from interpretune.analysis.ops.base import AnalysisBatch\n",
"from interpretune.config import AnalysisCfg, init_analysis_cfgs\n",
"\n",
"module.analysis_cfg = AnalysisCfg(target_op=it.compute_attribution_graph, ignore_manual=True, save_tokens=False)\n",
"init_analysis_cfgs(module, [module.analysis_cfg])\n",
"\n",
"fruits = [\"apple\", \"banana\", \"grape\", \"peach\"]\n",
"colors = [\"red\", \"blue\", \"green\", \"yellow\"]\n",
"if CHAT_FORMAT_PROMPT:\n",
" # instruction-tuned replacement models assert chat-formatted inputs\n",
" from it_examples.example_prompt_configs import GemmaPromptConfig\n",
"\n",
" prompt = GemmaPromptConfig().apply_chat_template_fn(\n",
" tokenizer, CONCEPT_PROMPT, tokenize=False, add_generation_prompt=True\n",
" )\n",
"else:\n",
" prompt = CONCEPT_PROMPT\n",
"\n",
"# sign-aware, influence-normalized scaling (the validated s5_any lineage)\n",
"ct_cfg = module.it_cfg.circuit_tracer_cfg\n",
"ct_cfg.intervention_sign_aware_scale = True\n",
"ct_cfg.intervention_max_influence_norm_scale = True\n",
"ct_cfg.intervention_value_source = \"top_feature_activation_values\"\n",
"\n",
"selection_spec = FeatureSelectionSpec(\n",
" layer_slice=slice(FEATURE_SELECTION_MIN_LAYER, None),\n",
" score_source=\"signed_influence\",\n",
" score_sign=FEATURE_SELECTION_SCORE_SIGN,\n",
" rank_by_abs=True,\n",
")\n",
"pipeline_results = it.intervention_from_concept(\n",
" module,\n",
" AnalysisBatch(\n",
" concept_group_a=fruits,\n",
" concept_group_b=colors,\n",
" concept_label=\"Concept: Fruit - Color\",\n",
" concept_direction_mode=\"paired_rejection\",\n",
" prompts=[prompt],\n",
" ),\n",
" None,\n",
" 0,\n",
" top_n=FEATURE_SELECTION_TOP_N,\n",
" intervention_scale_factor=INTERVENTION_SCALE_FACTOR,\n",
" feature_selection=selection_spec,\n",
")\n",
"# one call renders the linked/signed features table + the consolidated target-gap table and\n",
"# returns everything later phases need (features, direction, target ids, gaps)\n",
"DASHBOARD_BASE_URL = LOCAL_WEBAPP_URL\n",
"steering_base_url = DASHBOARD_BASE_URL\n",
"steering = display_steering_results(\n",
" pipeline_results,\n",
" tokenizer,\n",
" CONCEPT_TARGET_TOKENS,\n",
" neuronpedia_model=NEURONPEDIA_MODEL_ID,\n",
" neuronpedia_set=NEURONPEDIA_SOURCE_SET,\n",
" neuronpedia_base_url=steering_base_url,\n",
" min_layer=FEATURE_SELECTION_MIN_LAYER,\n",
")\n",
"steered_features = steering.steered_features\n",
"pipeline_direction = steering.direction\n",
"target_a_id, target_b_id = steering.target_ids\n",
"fm_pre_gap, fm_post_gap = steering.pre_gap, steering.post_gap\n",
"assert fm_post_gap > fm_pre_gap, \"feature-mediated steering should push the gap toward the target concept\""
]
},
{
"cell_type": "markdown",
"id": "7623eae2785240b9bd12b16a66d81610",
"metadata": {
"papermill": {
"duration": 0.008781,
"end_time": "2026-07-31T21:35:57.441718+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:57.432937+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## 3. Feature semantics: top-features table + local explanation coverage\n",
"\n",
"The steered features render as a table with the `(layer, pos, feature)` node tuple linked to its\n",
"dashboard, the **signed** influence score (Sign / |Score| columns — the `signed_influence`\n",
"selection can steer with negative-signed features, so the sign is colour-coded), and a best-effort\n",
"**Explanation** column resolved from the local webapp's feature API.\n",
"\n",
"`ensure_local_feature_explanations` first reports local explanation coverage and, when\n",
"`GENERATE_MISSING_LOCAL_EXPLANATIONS=True`, backfills missing explanations through the conforming\n",
"explanation CLI (see `docs/neuronpedia_dashboard_pipeline.md`, \"Explanation CLI configuration\").\n"
]
},
{
"cell_type": "code",
"execution_count": 7,
"id": "7cdc8c89c7104fffa095e18ddfef8986",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:35:57.460225Z",
"iopub.status.busy": "2026-07-31T21:35:57.460021Z",
"iopub.status.idle": "2026-07-31T21:39:24.197028Z",
"shell.execute_reply": "2026-07-31T21:39:24.196031Z"
},
"papermill": {
"duration": 206.747696,
"end_time": "2026-07-31T21:39:24.197973+00:00",
"exception": false,
"start_time": "2026-07-31T21:35:57.450277+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"local explanation coverage: 5/5\n",
"explanations generated this run: 5\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
" | # | Node | Sign | |Score| | Explanation |
|---|
| 1 | (25, 27, 1316) | − | 2.55e-08 | fruits |
| 2 | (25, 27, 765) | − | 1.74e-08 | code |
| 3 | (16, 27, 155) | + | 1.04e-08 | fruit |
| 4 | (23, 27, 725) | − | 6.98e-09 | proper names |
| 5 | (25, 27, 662) | − | 6.41e-09 | syntax delimiters |
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# @title 3: Top-features table + local explanation coverage { display-mode: \"form\" }\n",
"# top_feature_ids are (layer, position, feature) tuples; dashboards/explanations are per\n",
"# (layer, feature), so collapse positions while preserving selection order\n",
"steered_layer_feature_pairs = list(dict.fromkeys((f[0], f[-1]) for f in steered_features))\n",
"\n",
"feature_refs = feature_tuples_to_feature_refs(\n",
" model_id=NEURONPEDIA_MODEL_ID,\n",
" source_set=NEURONPEDIA_SOURCE_SET,\n",
" feature_tuples=steered_layer_feature_pairs,\n",
" base_url=DASHBOARD_BASE_URL,\n",
")\n",
"coverage = ensure_local_feature_explanations(\n",
" feature_refs,\n",
" generate_missing=GENERATE_MISSING_LOCAL_EXPLANATIONS,\n",
" regenerate_existing=REGENERATE_LOCAL_EXPLANATIONS,\n",
" local_db_url=LOCAL_DB_URL,\n",
")\n",
"covered = len(coverage.statuses) - len(coverage.missing_feature_refs)\n",
"print(f\"local explanation coverage: {covered}/{len(coverage.statuses)}\")\n",
"if coverage.generated_artifacts:\n",
" print(f\"explanations generated this run: {len(coverage.generated_artifacts)}\")\n",
"if coverage.generation_failures:\n",
" print(\"generation failures:\", [f.error for f in coverage.generation_failures])\n",
"\n",
"# Best-effort explanation text from the local webapp's feature API; unmapped features simply\n",
"# render an empty Explanation cell\n",
"feature_explanations = resolve_feature_explanations(\n",
" model_id=NEURONPEDIA_MODEL_ID,\n",
" source_set=NEURONPEDIA_SOURCE_SET,\n",
" feature_tuples=steered_layer_feature_pairs,\n",
" base_url=DASHBOARD_BASE_URL,\n",
")\n",
"\n",
"display_top_features_comparison(\n",
" {\"Steered Features (signed influence)\": steered_features},\n",
" {\"Steered Features (signed influence)\": pipeline_results.top_feature_scores.tolist()},\n",
" neuronpedia_model=NEURONPEDIA_MODEL_ID,\n",
" neuronpedia_set=NEURONPEDIA_SOURCE_SET,\n",
" neuronpedia_base_url=DASHBOARD_BASE_URL,\n",
" show_score_sign=True,\n",
" feature_explanations=feature_explanations,\n",
")"
]
},
{
"cell_type": "markdown",
"id": "b118ea5561624da68c537baed56e602f",
"metadata": {
"papermill": {
"duration": 0.008723,
"end_time": "2026-07-31T21:39:24.215902+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:24.207179+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## 4. Direct-hook path: concept direction -> hook-tensor steering\n",
"\n",
"Recomputes the embed-basis concept direction for the same concept pair (a consistency check against\n",
"the step 2 pipeline's direction — cosine should be ~1.0 since both derive from the same\n",
"embedding-basis `paired_rejection`) and applies `it.model_fwd_intervention(...)` at\n",
"`EMBED_INTERVENTION_HOOK` in `EMBED_INTERVENTION_MODE` mode, comparing\n",
"`pre/post_intervention_logits` and the target-token gap against the feature-mediated result. The\n",
"same direction steered through selected transcoder features vs added directly at the hook point\n",
"produces different effect sizes — the feature-mediated path is typically stronger per unit scale.\n"
]
},
{
"cell_type": "code",
"execution_count": 8,
"id": "938c804e27f84196a10c8828c723f798",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:39:24.234777Z",
"iopub.status.busy": "2026-07-31T21:39:24.234571Z",
"iopub.status.idle": "2026-07-31T21:39:24.803648Z",
"shell.execute_reply": "2026-07-31T21:39:24.802837Z"
},
"papermill": {
"duration": 0.57982,
"end_time": "2026-07-31T21:39:24.804497+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:24.224677+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"pipeline-vs-direct direction cosine: +1.0000 (~1.0 expected — same embed-basis construction)\n"
]
},
{
"data": {
"text/html": [
"\n",
" \n",
"
Direct-hook steering — target gap
\n",
"
\n",
" \n",
" \n",
" | Token | \n",
" Pre prob | \n",
" Post prob | \n",
" Pre logit | \n",
" Post logit | \n",
" Δ | \n",
"
\n",
" \n",
" \n",
" | Fruit | 4.31e-04 | 7.586% | 41.5000 | 48.7500 | +7.2500 |
\n",
"| Color | 99.957% | 92.414% | 49.2500 | 51.2500 | +2.0000 |
\n",
"| Gap (Fruit − Color) | | | -7.7500 | -2.5000 | +5.2500 |
\n",
"\n",
" \n",
"
\n",
"
\n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stdout",
"output_type": "stream",
"text": [
"feature-mediated delta +48.250 vs direct-hook delta +5.250\n"
]
}
],
"source": [
"# @title 4: Direct-hook steering { display-mode: \"form\" }\n",
"# Recompute the embed-basis concept direction for the same concept pair (no store rows -> embed basis)\n",
"direct_result = it.concept_direction(\n",
" module,\n",
" AnalysisBatch(\n",
" concept_group_a=fruits,\n",
" concept_group_b=colors,\n",
" concept_label=\"Concept: Fruit - Color (direct)\",\n",
" concept_direction_mode=\"paired_rejection\",\n",
" ),\n",
" None,\n",
" 0,\n",
")\n",
"direct_direction = direct_result.concept_direction.detach()\n",
"cosine = torch.nn.functional.cosine_similarity(\n",
" pipeline_direction, direct_direction.float().cpu().reshape(-1), dim=0\n",
").item()\n",
"print(f\"pipeline-vs-direct direction cosine: {cosine:+.4f} (~1.0 expected — same embed-basis construction)\")\n",
"\n",
"# Direct hook-tensor intervention at the canonical hook point\n",
"module.analysis_cfg = AnalysisCfg(target_op=it.model_fwd_intervention, ignore_manual=True, save_tokens=False)\n",
"init_analysis_cfgs(module, [module.analysis_cfg])\n",
"\n",
"# chat-rendered prompts already carry their special tokens; plain completion prompts need them added\n",
"enc = tokenizer(prompt, return_tensors=\"pt\", padding=False, add_special_tokens=not CHAT_FORMAT_PROMPT)\n",
"device = next(module.model.parameters()).device\n",
"if BACKEND == \"transformerlens\":\n",
" # HookedTransformer.forward takes `input`, not the HF-style `input_ids`/`attention_mask` keys\n",
" batch = {\"input\": enc[\"input_ids\"].to(device)}\n",
"else:\n",
" batch = {k: (v.to(device) if isinstance(v, torch.Tensor) else v) for k, v in dict(enc).items()}\n",
"\n",
"# legacy HookedTransformer models (the CT TransformerLens backend) expose no `unembed.hook_in`;\n",
"# their pre-unembed equivalent is `ln_final.hook_normalized` (alias-map expansion tracked in\n",
"# interpretune#223)\n",
"intervention_hook = EMBED_INTERVENTION_HOOK\n",
"if BACKEND == \"transformerlens\" and EMBED_INTERVENTION_HOOK == \"unembed.hook_in\":\n",
" intervention_hook = \"ln_final.hook_normalized\"\n",
"\n",
"direct_batch = AnalysisBatch(\n",
" prompts=[prompt],\n",
" concept_direction=direct_direction,\n",
" logit_target_ids=torch.tensor([target_a_id], dtype=torch.long),\n",
" concept_group_a_token_ids=[target_a_id],\n",
" concept_group_b_token_ids=[target_b_id],\n",
" concept_cache_key=intervention_hook,\n",
" intervention_hook_pattern=intervention_hook,\n",
" intervention_mode=EMBED_INTERVENTION_MODE,\n",
" direction_scale_factor=INTERVENTION_SCALE_FACTOR,\n",
")\n",
"direct_out = it.model_fwd_intervention(module, direct_batch, batch, 0)\n",
"\n",
"direct_pre_gap, direct_post_gap = display_target_gap(\n",
" direct_out.pre_intervention_logits.float().cpu().reshape(-1),\n",
" direct_out.post_intervention_logits.float().cpu().reshape(-1),\n",
" (CONCEPT_TARGET_TOKENS[0], target_a_id),\n",
" (CONCEPT_TARGET_TOKENS[1], target_b_id),\n",
" title=\"Direct-hook steering — target gap\",\n",
")\n",
"print(\n",
" f\"feature-mediated delta {fm_post_gap - fm_pre_gap:+.3f} vs direct-hook delta \"\n",
" f\"{direct_post_gap - direct_pre_gap:+.3f}\"\n",
")\n",
"assert direct_post_gap > direct_pre_gap, \"direct-hook steering should push the gap toward the target concept\""
]
},
{
"cell_type": "markdown",
"id": "504fb2a444614c0babb325280ed9130a",
"metadata": {
"papermill": {
"duration": 0.00922,
"end_time": "2026-07-31T21:39:24.823338+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:24.814118+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## 5. User-curated feature steering (OPTIONAL — off by default)\n",
"\n",
"**This step is skipped unless you supply your own feature ids.** Curated ids index the transcoder's\n",
"feature space, so they are tied to a specific (model, source set) pair — valid across regenerations\n",
"of that same pair, but not transferable to another model, width or source set. What does not carry\n",
"over is the *reasoning* for a pick: the explanation that made a feature look like \"a clear fruit\n",
"feature\" describes dashboard evidence, and that evidence shifts when the prompt corpus changes.\n",
"Curated picks therefore only travel reliably alongside a shared dashboard artifact, which is not\n",
"available yet (priority item on the IT roadmap). Until then the lists in the parameters cell start\n",
"empty and this step reports that it is skipping.\n",
"\n",
"To run it, populate `CURATED_POSITIVE_FEATURES` / `CURATED_NEGATIVE_FEATURES` with features you\n",
"located in your own local webapp. What it then demonstrates: instead of letting the attribution graph\n",
"select features, it steers with features found by manual dashboard/inference search — positively\n",
"firing on the target concept, or writing against the competing concept. Sign control is direct —\n",
"`FeatureSelectionSpec.activation_overrides` pins each curated feature's intervention activation\n",
"(+magnitude to amplify, −magnitude to suppress), with sign-aware/influence-normalized scaling\n",
"disabled so the overrides apply as-is. Comparing that target gap against the attribution-selected\n",
"step 2 result probes how well graph-derived feature sets capture the concept-relevant circuitry a\n",
"human finds by direct inspection.\n",
"\n",
"This becomes a sensible default once generated dashboards are downloadable from the Hub and everyone\n",
"shares one substrate with stable ids.\n"
]
},
{
"cell_type": "code",
"execution_count": 9,
"id": "59bbdb311c014d738909a11f9e486628",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:39:24.843666Z",
"iopub.status.busy": "2026-07-31T21:39:24.843536Z",
"iopub.status.idle": "2026-07-31T21:39:24.849871Z",
"shell.execute_reply": "2026-07-31T21:39:24.849028Z"
},
"papermill": {
"duration": 0.017566,
"end_time": "2026-07-31T21:39:24.850577+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:24.833011+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"name": "stdout",
"output_type": "stream",
"text": [
"Skipping curated-feature steering: no curated features configured (disabled by default).\n",
"Curated ids are tied to a specific (model, source set) pair, so this step needs ids you located in YOUR local webapp -- see the parameters cell.\n"
]
}
],
"source": [
"# @title 5: User-curated feature steering { display-mode: \"form\" }\n",
"if not (CURATED_POSITIVE_FEATURES or CURATED_NEGATIVE_FEATURES):\n",
" print(\n",
" \"Skipping curated-feature steering: no curated features configured (disabled by default).\\n\"\n",
" \"Curated ids are tied to a specific (model, source set) pair, so this step needs ids you \"\n",
" \"located in YOUR local webapp -- see the parameters cell.\"\n",
" )\n",
"elif NEURONPEDIA_SOURCE_SET != CURATED_FEATURES_SOURCE_SET:\n",
" print(\n",
" f\"Skipping curated-feature steering: the curated features target {CURATED_FEATURES_SOURCE_SET!r} \"\n",
" f\"but this run uses {NEURONPEDIA_SOURCE_SET!r}\"\n",
" )\n",
"else:\n",
" module.analysis_cfg = AnalysisCfg(target_op=it.compute_attribution_graph, ignore_manual=True, save_tokens=False)\n",
" init_analysis_cfgs(module, [module.analysis_cfg])\n",
"\n",
" # direct sign control via activation overrides (positive = amplify, negative = suppress);\n",
" # disable sign-aware/influence-normalized scaling so the overrides are applied as-is\n",
" ct_cfg.intervention_sign_aware_scale = False\n",
" ct_cfg.intervention_max_influence_norm_scale = False\n",
" curated_pairs = [tuple(p) for p in (*CURATED_POSITIVE_FEATURES, *CURATED_NEGATIVE_FEATURES)]\n",
" curated_overrides = {tuple(p): float(CURATED_OVERRIDE_MAGNITUDE) for p in CURATED_POSITIVE_FEATURES}\n",
" curated_overrides.update({tuple(p): -float(CURATED_OVERRIDE_MAGNITUDE) for p in CURATED_NEGATIVE_FEATURES})\n",
" curated_spec = FeatureSelectionSpec(\n",
" layer_feature_pairs=curated_pairs,\n",
" activation_overrides=curated_overrides,\n",
" )\n",
" curated_results = it.intervention_from_concept(\n",
" module,\n",
" AnalysisBatch(\n",
" concept_group_a=fruits,\n",
" concept_group_b=colors,\n",
" concept_label=\"Concept: Fruit - Color (curated)\",\n",
" concept_direction_mode=\"paired_rejection\",\n",
" prompts=[prompt],\n",
" ),\n",
" None,\n",
" 0,\n",
" top_n=len(curated_pairs),\n",
" intervention_scale_factor=INTERVENTION_SCALE_FACTOR,\n",
" feature_selection=curated_spec,\n",
" )\n",
" curated_feature_pairs = [(int(f[0]), int(f[-1])) for f in curated_results.top_feature_ids]\n",
" curated_explanations = resolve_feature_explanations(\n",
" model_id=NEURONPEDIA_MODEL_ID,\n",
" source_set=NEURONPEDIA_SOURCE_SET,\n",
" feature_tuples=curated_feature_pairs,\n",
" base_url=DASHBOARD_BASE_URL,\n",
" )\n",
" curated = display_steering_results(\n",
" curated_results,\n",
" tokenizer,\n",
" CONCEPT_TARGET_TOKENS,\n",
" neuronpedia_model=NEURONPEDIA_MODEL_ID,\n",
" neuronpedia_set=NEURONPEDIA_SOURCE_SET,\n",
" neuronpedia_base_url=DASHBOARD_BASE_URL,\n",
" feature_explanations=curated_explanations,\n",
" features_label=\"Curated Features (manual search)\",\n",
" gap_title=\"Curated-feature steering — target gap\",\n",
" )\n",
" print(\n",
" f\"attribution-selected delta {fm_post_gap - fm_pre_gap:+.3f} vs \"\n",
" f\"curated-feature delta {curated.post_gap - curated.pre_gap:+.3f}\"\n",
" )\n",
" # restore the sign-aware defaults for any later cells / re-runs\n",
" ct_cfg.intervention_sign_aware_scale = True\n",
" ct_cfg.intervention_max_influence_norm_scale = True"
]
},
{
"cell_type": "markdown",
"id": "b43b363d81ae4b689946ece5c682cd59",
"metadata": {
"papermill": {
"duration": 0.009259,
"end_time": "2026-07-31T21:39:24.869942+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:24.860683+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## 6. Input/output decoupling analysis (graph hydration + UMAP)\n",
"\n",
"Attribution-selected steering features are chosen for their *output* effect (decoder projection\n",
"onto the target logit difference), while dashboard explanations describe their *input* behavior\n",
"(the contexts they fire on) — the two can decouple sharply. A recurring special case is the\n",
"suppressor-motif exemplar: a feature that *fires on concept contexts yet projects against the\n",
"concept token* (redundancy suppression under next-token training) — causally ideal for sign-aware\n",
"steering, semantically confusing on its dashboard. This step demonstrates those mechanics\n",
"directly, and in doing so demos the framework's graph hydration capability\n",
"(`analysis_backend.hydrate_graph_from_batch`) for detailed post-hoc analysis of a persisted\n",
"attribution result:\n",
"\n",
"1. hydrate the step-2 attribution graph; highlight the prompt's concept-token positions;\n",
"2. compute each analyzed feature's input profile (activation mass at concept positions) and\n",
" output profile (signed decoder projection onto the unit target-token unembed difference)\n",
" via the shared `feature_io_profiles` helper;\n",
"3. render the decoupling table (signature column flags `decoupled` and `suppressor-motif` rows);\n",
"4. project decoder vectors to 2D (UMAP, PCA fallback) with hover details per analyzed feature. Axis tick\n",
"numbers are intentionally hidden of course since UMAP coordinates are non-metric (arbitrary rotation/scale; only local neighborhood structure is meaningful).\n",
"\n",
"Expect roughly 2 of the 5 attribution picks to be input-aligned (\"fruits\", \"ripe fruit\"), including\n",
"a suppressor-motif exemplar (\"fruits\" firing on concept while projecting against `Fruit`), with the\n",
"rest decoupled (zero input concept share). If you enabled the optional step 5, its curated features\n",
"also join this analysis — typically with high input shares but the smallest |output projections|,\n",
"which is the measured explanation for why curated steering tends to be weaker.\n"
]
},
{
"cell_type": "code",
"execution_count": 10,
"id": "8a65eabff63a45729fe45fb5ade58bdc",
"metadata": {
"execution": {
"iopub.execute_input": "2026-07-31T21:39:24.889376Z",
"iopub.status.busy": "2026-07-31T21:39:24.889253Z",
"iopub.status.idle": "2026-07-31T21:39:40.689833Z",
"shell.execute_reply": "2026-07-31T21:39:40.688939Z"
},
"papermill": {
"duration": 15.812026,
"end_time": "2026-07-31T21:39:40.691135+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:24.879109+00:00",
"status": "completed"
},
"tags": []
},
"outputs": [
{
"data": {
"text/html": [
"Prompt tokens — concept positions highlighted
<bos><start_of_turn>user\n",
"Is orange a color or a fruit? Answer with one word: Color or Fruit. orange -><end_of_turn>\n",
"<start_of_turn>model\n",
"
concept-token positions: [5, 7, 10, 17, 19, 21]
"
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"data": {
"text/html": [
"\n",
" \n",
"
Feature input/output decoupling
\n",
"
\n",
" \n",
" | Feature | \n",
" Input concept share | \n",
" Act mass | \n",
" Output proj (Fruit-Color) | \n",
" Signature | \n",
" Explanation | \n",
"
\n",
" | L25/1316 | 0.455 | 1918.25 | -0.2458 | suppressor-motif | fruits |
\n",
"| L16/155 | 0.841 | 853.25 | +0.1884 | | fruit |
\n",
"| L25/662 | 0.000 | 242.00 | -0.0349 | decoupled | syntax delimiters |
\n",
"| L25/765 | 0.000 | 506.00 | +0.0348 | decoupled | code |
\n",
"| L23/725 | 0.000 | 669.00 | +0.0167 | | proper names |
\n",
"\n",
"
\n",
"
decoupled = large |output proj| with ~zero input concept share;\n",
" suppressor-motif = fires on concept contexts yet projects against the concept token.
\n",
"
\n",
" "
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
},
{
"name": "stderr",
"output_type": "stream",
"text": [
"/mnt/cache/speediedan/.venvs/it_latest/lib/python3.13/site-packages/umap/umap_.py:1952: UserWarning: n_jobs value 1 overridden to 1 by setting random_state. Use no seed for parallelism.\n",
" warn(\n"
]
},
{
"data": {
"text/html": [
""
],
"text/plain": [
""
]
},
"metadata": {},
"output_type": "display_data"
}
],
"source": [
"# @title 6: Decoupling analysis via hydrated graph + UMAP { display-mode: \"form\" }\n",
"import numpy as np\n",
"\n",
"from interpretune.analysis.backends import require_analysis_backend\n",
"from it_examples.utils.example_helpers import concept_token_positions, feature_io_profiles\n",
"from it_examples.utils.nb_ui_utils import (\n",
" display_concept_positions,\n",
" display_feature_decoupling_table,\n",
" plot_decoder_projection_map,\n",
")\n",
"\n",
"analysis_backend = require_analysis_backend(module)\n",
"graph = analysis_backend.hydrate_graph_from_batch(pipeline_results)\n",
"\n",
"# concept-token positions derived from the demo's own concept groups + probe/target tokens\n",
"concept_words = {w.lower() for w in (*fruits, *colors, *CONCEPT_TARGET_TOKENS, \"orange\")}\n",
"prompt_token_ids = [int(t) for t in graph.input_tokens]\n",
"concept_positions = concept_token_positions(tokenizer, prompt_token_ids, sorted(concept_words))\n",
"display_concept_positions(tokenizer, prompt_token_ids, concept_positions)\n",
"\n",
"embed_weight = analysis_backend.get_embedding_weight(module).detach().float().cpu()\n",
"target_diff = embed_weight[target_a_id] - embed_weight[target_b_id]\n",
"target_diff = target_diff / target_diff.norm()\n",
"target_label = f\"{CONCEPT_TARGET_TOKENS[0]}-{CONCEPT_TARGET_TOKENS[1]}\"\n",
"\n",
"analyzed_pairs = list(dict.fromkeys((int(f[0]), int(f[-1])) for f in steered_features))\n",
"# Merge in the step-5 curated features so the decoupling table can show why curated steering is\n",
"# weaker (high input share, smallest |output projection|). The guard tests the name actually bound\n",
"# by step 5: it previously tested \"curated\", which is never defined, so the curated features were\n",
"# silently never analyzed and the discussion below described rows that were not in the table.\n",
"if \"curated_feature_pairs\" in globals():\n",
" analyzed_pairs += [pair for pair in curated_feature_pairs if pair not in analyzed_pairs]\n",
"all_explanations = dict(feature_explanations)\n",
"if \"curated_explanations\" in globals():\n",
" all_explanations.update(curated_explanations)\n",
"\n",
"transcoder_set = getattr(module.replacement_model.transcoders, \"_module\", module.replacement_model.transcoders)\n",
"profiles = feature_io_profiles(graph, analyzed_pairs, target_diff, transcoder_set, concept_positions)\n",
"display_feature_decoupling_table(profiles, all_explanations, target_label=target_label)\n",
"\n",
"# decoder vectors for the interactive projection map (analyzed + random active-feature background)\n",
"rng = np.random.default_rng(17)\n",
"active_rows = graph.active_features.cpu()\n",
"background_pool = sorted({(int(r[0]), int(r[2])) for r in active_rows} - set(analyzed_pairs))\n",
"background_idx = rng.choice(len(background_pool), size=min(300, len(background_pool)), replace=False)\n",
"background_pairs = [background_pool[i] for i in background_idx]\n",
"\n",
"\n",
"def _decoder_rows(pairs):\n",
" return torch.stack(\n",
" [transcoder_set._get_decoder_vectors(lyr, torch.tensor([ft]))[0].detach().float().cpu() for lyr, ft in pairs]\n",
" )\n",
"\n",
"\n",
"plot_decoder_projection_map(\n",
" profiles,\n",
" _decoder_rows(analyzed_pairs),\n",
" _decoder_rows(background_pairs),\n",
" feature_explanations=all_explanations,\n",
" target_label=target_label,\n",
" title=\"Steering-feature decoder map\",\n",
")"
]
},
{
"cell_type": "markdown",
"id": "c3933fab20d04ec698c2621248eb3be0",
"metadata": {
"papermill": {
"duration": 0.009879,
"end_time": "2026-07-31T21:39:40.711364+00:00",
"exception": false,
"start_time": "2026-07-31T21:39:40.701485+00:00",
"status": "completed"
},
"tags": []
},
"source": [
"## Summary\n",
"\n",
"- Feature-mediated and direct-hook steering paths (plus the optional user-curated path) on one proven\n",
" example, one backend per run — all driven by the same embed-basis concept direction.\n",
"- Semantic grounding via a local Neuronpedia dev webapp, including optional local explanation\n",
" generation — the full local pipeline: dashboards -> explanations -> selection -> steering.\n",
"- Input/output decoupling mechanics demonstrated via graph hydration + decoder-space UMAP,\n",
" doubling as a demo of persisted-graph post-hoc analysis.\n",
"- The zero-setup public-dashboard version:\n",
" [`ct_concept_steering_demo.ipynb`](ct_concept_steering_demo.ipynb).\n",
"- Deeper coverage of the underlying op pipeline (per-op invocation, native + hub composition):\n",
" see `ct_analysis_backend_demo.ipynb`. Capability map:\n",
" `tests/nb_experiments/intervention_capabilities_overview.md`.\n"
]
}
],
"metadata": {
"kernelspec": {
"display_name": "it_latest (3.13.11.final.0)",
"language": "python",
"name": "python3"
},
"language_info": {
"codemirror_mode": {
"name": "ipython",
"version": 3
},
"file_extension": ".py",
"mimetype": "text/x-python",
"name": "python",
"nbconvert_exporter": "python",
"pygments_lexer": "ipython3",
"version": "3.13.11"
},
"papermill": {
"default_parameters": {},
"duration": 279.385293,
"end_time": "2026-07-31T21:39:44.366026+00:00",
"environment_variables": {},
"exception": null,
"input_path": "/home/speediedan/repos/interpretune/src/it_examples/notebooks/publish/circuit_tracer_examples/ct_concept_steering_demo_local_np.ipynb",
"output_path": "/home/speediedan/repos/interpretune/docs/notebook_artifacts/circuit_tracer_examples/ct_concept_steering_demo_local_np.ipynb",
"parameters": {
"GENERATE_MISSING_LOCAL_EXPLANATIONS": true,
"REGENERATE_LOCAL_EXPLANATIONS": true
},
"start_time": "2026-07-31T21:35:04.980733+00:00",
"version": "2.7.0"
},
"widgets": {
"application/vnd.jupyter.widget-state+json": {
"state": {
"008376e6006f4a448de13c7ab19525a4": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_665c3e2508fd42ee89f26bea38677d42",
"max": 277.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_2a8c97eda79b49af9756651507cb1dd7",
"tabbable": null,
"tooltip": null,
"value": 277.0
}
},
"0228514401124e8b881f456d54c923e8": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"0420102325274a948db9163d3d45fa85": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"0578025f5699419983810812e656e9d3": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"0698e0c38ad848a8968db82c8d5c1f56": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_da303a40c3f5420694527eddf72676f4",
"placeholder": "",
"style": "IPY_MODEL_f61725fdd30e4f03ae4ced3fe8df4166",
"tabbable": null,
"tooltip": null,
"value": " 3000/3000 [00:00<00:00, 184519.11 examples/s]"
}
},
"06ba4b01c6ba49159da6a584e2599398": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_6e5a16f20f284bb3a3d907cc22d5d260",
"placeholder": "",
"style": "IPY_MODEL_64077b92ee9c4259b260f9ea361a54ba",
"tabbable": null,
"tooltip": null,
"value": " 3000/3000 [00:00<00:00, 15731.37 examples/s]"
}
},
"07d517a822d4418ca30ed7e31ebdbf50": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"086b9c6707534233a4953dbcedb9675a": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"09ada85d78f948d3829407e62f4906c9": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"0ebd5119c4bc4c35a6f1d88a5772fe2e": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_9b5688a27c824997baea004a34fc7c00",
"placeholder": "",
"style": "IPY_MODEL_57818cf3d6ce420fb9378de9e282fb7b",
"tabbable": null,
"tooltip": null,
"value": " 277/277 [00:00<00:00, 7523.78 examples/s]"
}
},
"112f478b6dfc4319a0ef8f9c7112c6ab": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1183a4644e414dfaa077abe9dedb4276": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"16361f64cf2740ee9e0076ebdda4ff98": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_0228514401124e8b881f456d54c923e8",
"placeholder": "",
"style": "IPY_MODEL_ba9b19a6ea984f1581bf764e483426ab",
"tabbable": null,
"tooltip": null,
"value": " 340/340 [00:01<00:00, 269.07it/s]"
}
},
"176d6618ffb94f86be27ce6d399a591f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"1bf85b9c05ca4807858e093331329389": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_ab6a55e914e14f1fbf9e4b705dbb74b9",
"placeholder": "",
"style": "IPY_MODEL_8e0d1fd3b9c6459ca45eb203eec9eeb1",
"tabbable": null,
"tooltip": null,
"value": " 0.00/0.00 [00:01<?, ?B/s]"
}
},
"1d047fd4bd2e4e1c8a0f22c24033402c": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"1d79881ce6614a58bcb9ce58b6acaff0": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_20575a19729248268cc2053d3ca8bff4",
"IPY_MODEL_008376e6006f4a448de13c7ab19525a4",
"IPY_MODEL_6ea5713f81004ca99b1f2bb542a4a8b1"
],
"layout": "IPY_MODEL_4710d4da7e7849899ab50e9f6d137730",
"tabbable": null,
"tooltip": null
}
},
"20575a19729248268cc2053d3ca8bff4": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_69b1d59211144a429c9416b7babb234e",
"placeholder": "",
"style": "IPY_MODEL_176d6618ffb94f86be27ce6d399a591f",
"tabbable": null,
"tooltip": null,
"value": "Saving the dataset (1/1 shards): 100%"
}
},
"216ab738fe604c78b074585e89d94bcd": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"29d7e81df4ca471dbb15f201b9acb33b": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"2a1db43a88984974aecee6a3477140d5": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"2a8c97eda79b49af9756651507cb1dd7": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"2fa89b71d0014dd9a3d027f7ecd25403": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_daf73618f42e4cf68c5dca55e9971a51",
"IPY_MODEL_a6a95e601da345df98d45e043302c63a",
"IPY_MODEL_0698e0c38ad848a8968db82c8d5c1f56"
],
"layout": "IPY_MODEL_514051c5cdc9482bb63fabb577148dc6",
"tabbable": null,
"tooltip": null
}
},
"2fc965aa8c6d4e24ba5f25aebccc416e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"30cdbfce140f44b7a36aade1dbf10ad5": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_8958086da83d4da497641a7a9879fa56",
"placeholder": "",
"style": "IPY_MODEL_aa605b6538714f7daa9f4a15afb93b50",
"tabbable": null,
"tooltip": null,
"value": "Map: 100%"
}
},
"30dd7b332acc4fce8aa4deb2f0fac20c": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"30fb713670354962a230da199e456681": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"32cf7ed163b64afa970831de8897f572": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_112f478b6dfc4319a0ef8f9c7112c6ab",
"placeholder": "",
"style": "IPY_MODEL_086b9c6707534233a4953dbcedb9675a",
"tabbable": null,
"tooltip": null,
"value": "Map: 100%"
}
},
"344162a60e93454a89792bf3eeb5d8ef": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_c5cda575b4954da8b08325c7d89a4b3b",
"placeholder": "",
"style": "IPY_MODEL_cf89af05c797418eac956e2f701e137e",
"tabbable": null,
"tooltip": null,
"value": "Download complete: "
}
},
"461cea9cb47545e9863e34a1cfebe2b9": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_32cf7ed163b64afa970831de8897f572",
"IPY_MODEL_e65e699dd1594d5abc6f2a5e6739f99c",
"IPY_MODEL_06ba4b01c6ba49159da6a584e2599398"
],
"layout": "IPY_MODEL_8cb1ab64d7854321bc46c94f0aa44f69",
"tabbable": null,
"tooltip": null
}
},
"4710d4da7e7849899ab50e9f6d137730": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"47cbf1d58d314a01ae7e3c4f6ed66998": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": "20px"
}
},
"4a1d6c5c8d9543908ed9fcaa8cb6794e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"4ab624d825a843259680ca5aed9f4908": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"4d56f47906de465fb5b5484ace6d9ebf": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"4d9f75b005a14084b2642c2d4e5497f8": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_216ab738fe604c78b074585e89d94bcd",
"placeholder": "",
"style": "IPY_MODEL_c4ae0db3e26b4875a92589a63f39ff9c",
"tabbable": null,
"tooltip": null,
"value": " 26/26 [00:00<00:00, 2234.62it/s]"
}
},
"5067e7afc7b943fd953fc656873fd28e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"514051c5cdc9482bb63fabb577148dc6": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"55aec656124f449aa8534044f4ecdd6c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_6bced74fc1934a98871f95cf0c72de4b",
"max": 26.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_afa1c69af10949e08128b366fe92e54f",
"tabbable": null,
"tooltip": null,
"value": 26.0
}
},
"57818cf3d6ce420fb9378de9e282fb7b": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"5c706a0f3de54056a4c054e3ed5898bf": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"64077b92ee9c4259b260f9ea361a54ba": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"665c3e2508fd42ee89f26bea38677d42": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"66b8063a672841bea52cf548a9a69b93": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_4a1d6c5c8d9543908ed9fcaa8cb6794e",
"placeholder": "",
"style": "IPY_MODEL_29d7e81df4ca471dbb15f201b9acb33b",
"tabbable": null,
"tooltip": null,
"value": "Fetching 26 files: 100%"
}
},
"6753942e320a4699851444d1a78db9c2": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"69b1d59211144a429c9416b7babb234e": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"6a41b86b85634277a7384f40774fcdb2": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_30cdbfce140f44b7a36aade1dbf10ad5",
"IPY_MODEL_dc4476e8fe6e4d0198559d038aedf2e8",
"IPY_MODEL_d425757b1ecc4f428c8823b6dc35f21c"
],
"layout": "IPY_MODEL_8719e6b299f24b338fd92cda4a682060",
"tabbable": null,
"tooltip": null
}
},
"6bced74fc1934a98871f95cf0c72de4b": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"6cb91a8925674514a5e59227276af2a2": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_8eea10a142d74b2387a3f9f541ca38f5",
"IPY_MODEL_db668467e82d4dfa9d6cdd651508c243",
"IPY_MODEL_b160f23087714a38b70da061cb575451"
],
"layout": "IPY_MODEL_c0d6f5a99ff24a8e87473a4e427c7f62",
"tabbable": null,
"tooltip": null
}
},
"6de21306691d48f19e766884e012b832": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_07d517a822d4418ca30ed7e31ebdbf50",
"placeholder": "",
"style": "IPY_MODEL_d1984a1ae5124bfdacc038b86a352e3a",
"tabbable": null,
"tooltip": null,
"value": "Loading weights: 100%"
}
},
"6e5a16f20f284bb3a3d907cc22d5d260": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"6ea5713f81004ca99b1f2bb542a4a8b1": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_5c706a0f3de54056a4c054e3ed5898bf",
"placeholder": "",
"style": "IPY_MODEL_1183a4644e414dfaa077abe9dedb4276",
"tabbable": null,
"tooltip": null,
"value": " 277/277 [00:00<00:00, 30874.89 examples/s]"
}
},
"74b15a0f47464ba891687402fca75397": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_66b8063a672841bea52cf548a9a69b93",
"IPY_MODEL_55aec656124f449aa8534044f4ecdd6c",
"IPY_MODEL_4d9f75b005a14084b2642c2d4e5497f8"
],
"layout": "IPY_MODEL_ebd2964697bc41df8d58c8901909972f",
"tabbable": null,
"tooltip": null
}
},
"7da3eb95aada4a25b5906539cc6b9315": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_bb34feaad2a2453a9e40afe0b3e291b9",
"IPY_MODEL_8b019f797f8b416090b1a67fd1b109e3",
"IPY_MODEL_0ebd5119c4bc4c35a6f1d88a5772fe2e"
],
"layout": "IPY_MODEL_4ab624d825a843259680ca5aed9f4908",
"tabbable": null,
"tooltip": null
}
},
"808478f767c84bb194513201f0efc7a4": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"8719e6b299f24b338fd92cda4a682060": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"891fed20032146b08176ae447f691228": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"8958086da83d4da497641a7a9879fa56": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"8b019f797f8b416090b1a67fd1b109e3": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_09ada85d78f948d3829407e62f4906c9",
"max": 277.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_bef7688ae570455ab8c9f368419ce68b",
"tabbable": null,
"tooltip": null,
"value": 277.0
}
},
"8cb1ab64d7854321bc46c94f0aa44f69": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"8d052a40e8944aa99f8b736f609985af": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"8e0d1fd3b9c6459ca45eb203eec9eeb1": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"8ea35633a4b24ce2907ebb1846a98587": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_891fed20032146b08176ae447f691228",
"max": 340.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_2a1db43a88984974aecee6a3477140d5",
"tabbable": null,
"tooltip": null,
"value": 340.0
}
},
"8eea10a142d74b2387a3f9f541ca38f5": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_cbb8f73297bf47b5a2fe70248250d9db",
"placeholder": "",
"style": "IPY_MODEL_0420102325274a948db9163d3d45fa85",
"tabbable": null,
"tooltip": null,
"value": "Saving the dataset (1/1 shards): 100%"
}
},
"9b5688a27c824997baea004a34fc7c00": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"a6a95e601da345df98d45e043302c63a": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_808478f767c84bb194513201f0efc7a4",
"max": 3000.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_bdd39a92fdf844d9993d4885e3d671ff",
"tabbable": null,
"tooltip": null,
"value": 3000.0
}
},
"aa605b6538714f7daa9f4a15afb93b50": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"ab31c2943ef548e7b0651a503033d484": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"ab6a55e914e14f1fbf9e4b705dbb74b9": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"afa1c69af10949e08128b366fe92e54f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"afadb8341cd5430d98a44f638099d502": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"afcfbd20c5a74f2287c99cd7af907389": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"b160f23087714a38b70da061cb575451": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_1d047fd4bd2e4e1c8a0f22c24033402c",
"placeholder": "",
"style": "IPY_MODEL_df3cf25f3c344ba99011925987dbe348",
"tabbable": null,
"tooltip": null,
"value": " 2490/2490 [00:00<00:00, 137683.14 examples/s]"
}
},
"b91a53ad255240a5a5fa437774933b8d": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"ba9b19a6ea984f1581bf764e483426ab": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"bb34feaad2a2453a9e40afe0b3e291b9": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_0578025f5699419983810812e656e9d3",
"placeholder": "",
"style": "IPY_MODEL_6753942e320a4699851444d1a78db9c2",
"tabbable": null,
"tooltip": null,
"value": "Map: 100%"
}
},
"bdd39a92fdf844d9993d4885e3d671ff": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"bef7688ae570455ab8c9f368419ce68b": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"c0d6f5a99ff24a8e87473a4e427c7f62": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"c4ae0db3e26b4875a92589a63f39ff9c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"c5cda575b4954da8b08325c7d89a4b3b": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"ca87ab6448a44c309a7840e60d81faca": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_47cbf1d58d314a01ae7e3c4f6ed66998",
"max": 1.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_8d052a40e8944aa99f8b736f609985af",
"tabbable": null,
"tooltip": null,
"value": 0.0
}
},
"cbb8f73297bf47b5a2fe70248250d9db": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"cc9ca921550b4bcaa8c85ca500824cd0": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "ProgressStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "ProgressStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"bar_color": null,
"description_width": ""
}
},
"cf89af05c797418eac956e2f701e137e": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"d1984a1ae5124bfdacc038b86a352e3a": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"d425757b1ecc4f428c8823b6dc35f21c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_e324d4060158431c84c1f2bf459d6d54",
"placeholder": "",
"style": "IPY_MODEL_afcfbd20c5a74f2287c99cd7af907389",
"tabbable": null,
"tooltip": null,
"value": " 2490/2490 [00:00<00:00, 10846.17 examples/s]"
}
},
"d7dea835840840f0b6ff0d9bdf5c818c": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"da303a40c3f5420694527eddf72676f4": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"da8aa869221b47b7ae79ad8509ad14d7": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_6de21306691d48f19e766884e012b832",
"IPY_MODEL_8ea35633a4b24ce2907ebb1846a98587",
"IPY_MODEL_16361f64cf2740ee9e0076ebdda4ff98"
],
"layout": "IPY_MODEL_30fb713670354962a230da199e456681",
"tabbable": null,
"tooltip": null
}
},
"daf73618f42e4cf68c5dca55e9971a51": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HTMLView",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_b91a53ad255240a5a5fa437774933b8d",
"placeholder": "",
"style": "IPY_MODEL_4d56f47906de465fb5b5484ace6d9ebf",
"tabbable": null,
"tooltip": null,
"value": "Saving the dataset (1/1 shards): 100%"
}
},
"db668467e82d4dfa9d6cdd651508c243": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_30dd7b332acc4fce8aa4deb2f0fac20c",
"max": 2490.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_afadb8341cd5430d98a44f638099d502",
"tabbable": null,
"tooltip": null,
"value": 2490.0
}
},
"dc4476e8fe6e4d0198559d038aedf2e8": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_d7dea835840840f0b6ff0d9bdf5c818c",
"max": 2490.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_cc9ca921550b4bcaa8c85ca500824cd0",
"tabbable": null,
"tooltip": null,
"value": 2490.0
}
},
"df3cf25f3c344ba99011925987dbe348": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"e324d4060158431c84c1f2bf459d6d54": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"e65e699dd1594d5abc6f2a5e6739f99c": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "FloatProgressModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "FloatProgressModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "ProgressView",
"bar_style": "success",
"description": "",
"description_allow_html": false,
"layout": "IPY_MODEL_2fc965aa8c6d4e24ba5f25aebccc416e",
"max": 3000.0,
"min": 0.0,
"orientation": "horizontal",
"style": "IPY_MODEL_ab31c2943ef548e7b0651a503033d484",
"tabbable": null,
"tooltip": null,
"value": 3000.0
}
},
"ebd2964697bc41df8d58c8901909972f": {
"model_module": "@jupyter-widgets/base",
"model_module_version": "2.0.0",
"model_name": "LayoutModel",
"state": {
"_model_module": "@jupyter-widgets/base",
"_model_module_version": "2.0.0",
"_model_name": "LayoutModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "LayoutView",
"align_content": null,
"align_items": null,
"align_self": null,
"border_bottom": null,
"border_left": null,
"border_right": null,
"border_top": null,
"bottom": null,
"display": null,
"flex": null,
"flex_flow": null,
"grid_area": null,
"grid_auto_columns": null,
"grid_auto_flow": null,
"grid_auto_rows": null,
"grid_column": null,
"grid_gap": null,
"grid_row": null,
"grid_template_areas": null,
"grid_template_columns": null,
"grid_template_rows": null,
"height": null,
"justify_content": null,
"justify_items": null,
"left": null,
"margin": null,
"max_height": null,
"max_width": null,
"min_height": null,
"min_width": null,
"object_fit": null,
"object_position": null,
"order": null,
"overflow": null,
"padding": null,
"right": null,
"top": null,
"visibility": null,
"width": null
}
},
"f61725fdd30e4f03ae4ced3fe8df4166": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HTMLStyleModel",
"state": {
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HTMLStyleModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/base",
"_view_module_version": "2.0.0",
"_view_name": "StyleView",
"background": null,
"description_width": "",
"font_size": null,
"text_color": null
}
},
"fa492f0c13ae440db7ef0da54ef80b6f": {
"model_module": "@jupyter-widgets/controls",
"model_module_version": "2.0.0",
"model_name": "HBoxModel",
"state": {
"_dom_classes": [],
"_model_module": "@jupyter-widgets/controls",
"_model_module_version": "2.0.0",
"_model_name": "HBoxModel",
"_view_count": null,
"_view_module": "@jupyter-widgets/controls",
"_view_module_version": "2.0.0",
"_view_name": "HBoxView",
"box_style": "",
"children": [
"IPY_MODEL_344162a60e93454a89792bf3eeb5d8ef",
"IPY_MODEL_ca87ab6448a44c309a7840e60d81faca",
"IPY_MODEL_1bf85b9c05ca4807858e093331329389"
],
"layout": "IPY_MODEL_5067e7afc7b943fd953fc656873fd28e",
"tabbable": null,
"tooltip": null
}
}
},
"version_major": 2,
"version_minor": 0
}
}
},
"nbformat": 4,
"nbformat_minor": 5
}