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

Dataset: Open Web Text

Neuron 497 in Layer 4

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: 3.2143. Min Range: -3.2143

Max Act: 3.2143. Min Act: -0.1700

Data Index: 6110601 (Open Web Text)

Max Activating Token Index: 638

Text #1

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1780. Min Act: -0.1700

Data Index: 3092965 (Open Web Text)

Max Activating Token Index: 407

Text #2

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1694. Min Act: -0.1700

Data Index: 6761552 (Open Web Text)

Max Activating Token Index: 656

Text #3

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1747. Min Act: -0.1700

Data Index: 1561624 (Open Web Text)

Max Activating Token Index: 816

Text #4

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1437. Min Act: -0.1700

Data Index: 5445611 (Open Web Text)

Max Activating Token Index: 381

Text #5

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1606. Min Act: -0.1700

Data Index: 4512989 (Open Web Text)

Max Activating Token Index: 819

Text #6

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1624. Min Act: -0.1700

Data Index: 3331571 (Open Web Text)

Max Activating Token Index: 430

Text #7

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1524. Min Act: -0.1700

Data Index: 2641291 (Open Web Text)

Max Activating Token Index: 619

Text #8

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1332. Min Act: -0.1700

Data Index: 4613518 (Open Web Text)

Max Activating Token Index: 847

Text #9

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1499. Min Act: -0.1700

Data Index: 3892738 (Open Web Text)

Max Activating Token Index: 294

Text #10

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1251. Min Act: -0.1700

Data Index: 8390009 (Open Web Text)

Max Activating Token Index: 724

Text #11

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1374. Min Act: -0.1700

Data Index: 3865534 (Open Web Text)

Max Activating Token Index: 580

Text #12

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1183. Min Act: -0.1700

Data Index: 1182643 (Open Web Text)

Max Activating Token Index: 997

Text #13

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1032. Min Act: -0.1700

Data Index: 6605478 (Open Web Text)

Max Activating Token Index: 227

Text #14

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1025. Min Act: -0.1700

Data Index: 8752092 (Open Web Text)

Max Activating Token Index: 384

Text #15

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1052. Min Act: -0.1700

Data Index: 5327145 (Open Web Text)

Max Activating Token Index: 649

Text #16

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.0794. Min Act: -0.1700

Data Index: 6250118 (Open Web Text)

Max Activating Token Index: 780

Text #17

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1165. Min Act: -0.1700

Data Index: 1039451 (Open Web Text)

Max Activating Token Index: 401

Text #18

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.1054. Min Act: -0.1700

Data Index: 5445610 (Open Web Text)

Max Activating Token Index: 863

Text #19

Max Range: 3.2143. Min Range: -3.2143

Max Act: 3.0908. Min Act: -0.1700

Data Index: 3109203 (Open Web Text)

Max Activating Token Index: 665