Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1503 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 3.0606. Min Range: -3.0606

Max Act: 3.0603. Min Act: -0.1700

Data Index: 6199208 (Open Web Text)

Max Activating Token Index: 988

Text #1

Max Range: 3.0606. Min Range: -3.0606

Max Act: 3.0606. Min Act: -0.1700

Data Index: 4803631 (Open Web Text)

Max Activating Token Index: 414

Text #2

Max Range: 3.0606. Min Range: -3.0606

Max Act: 3.0196. Min Act: -0.1700

Data Index: 1767385 (Open Web Text)

Max Activating Token Index: 479

Text #3

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9892. Min Act: -0.1700

Data Index: 1151166 (Open Web Text)

Max Activating Token Index: 645

Text #4

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9926. Min Act: -0.1700

Data Index: 8246463 (Open Web Text)

Max Activating Token Index: 580

Text #5

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9628. Min Act: -0.1700

Data Index: 4173866 (Open Web Text)

Max Activating Token Index: 599

Text #6

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9863. Min Act: -0.1700

Data Index: 8196324 (Open Web Text)

Max Activating Token Index: 600

Text #7

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9666. Min Act: -0.1700

Data Index: 6662645 (Open Web Text)

Max Activating Token Index: 219

Text #8

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9166. Min Act: -0.1700

Data Index: 6141115 (Open Web Text)

Max Activating Token Index: 498

Text #9

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9617. Min Act: -0.1700

Data Index: 7150553 (Open Web Text)

Max Activating Token Index: 477

Text #10

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9495. Min Act: -0.1700

Data Index: 6425840 (Open Web Text)

Max Activating Token Index: 211

Text #11

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8937. Min Act: -0.1700

Data Index: 5779365 (Open Web Text)

Max Activating Token Index: 840

Text #12

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9020. Min Act: -0.1700

Data Index: 2836440 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.9061. Min Act: -0.1700

Data Index: 6234678 (Open Web Text)

Max Activating Token Index: 753

Text #14

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8964. Min Act: -0.1700

Data Index: 4874233 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8945. Min Act: -0.1700

Data Index: 7956636 (Open Web Text)

Max Activating Token Index: 376

Text #16

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8804. Min Act: -0.1700

Data Index: 7644625 (Open Web Text)

Max Activating Token Index: 288

Text #17

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8882. Min Act: -0.1700

Data Index: 3125952 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8844. Min Act: -0.1700

Data Index: 5878597 (Open Web Text)

Max Activating Token Index: 834

Text #19

Max Range: 3.0606. Min Range: -3.0606

Max Act: 2.8724. Min Act: -0.1700

Data Index: 1483306 (Open Web Text)

Max Activating Token Index: 735