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

Dataset: Open Web Text

Neuron 190 in Layer 6

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: 4.0339. Min Range: -4.0339

Max Act: 4.0339. Min Act: -0.1700

Data Index: 1034629 (Open Web Text)

Max Activating Token Index: 816

Text #1

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.9402. Min Act: -0.1700

Data Index: 6695521 (Open Web Text)

Max Activating Token Index: 818

Text #2

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.8862. Min Act: -0.1700

Data Index: 3730378 (Open Web Text)

Max Activating Token Index: 875

Text #3

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.8295. Min Act: -0.1700

Data Index: 6933045 (Open Web Text)

Max Activating Token Index: 392

Text #4

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7991. Min Act: -0.1700

Data Index: 5210574 (Open Web Text)

Max Activating Token Index: 982

Text #5

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7950. Min Act: -0.1700

Data Index: 3173836 (Open Web Text)

Max Activating Token Index: 279

Text #6

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7750. Min Act: -0.1700

Data Index: 935822 (Open Web Text)

Max Activating Token Index: 606

Text #7

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.8023. Min Act: -0.1700

Data Index: 8059982 (Open Web Text)

Max Activating Token Index: 903

Text #8

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.8207. Min Act: -0.1700

Data Index: 7894579 (Open Web Text)

Max Activating Token Index: 328

Text #9

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7659. Min Act: -0.1700

Data Index: 8382646 (Open Web Text)

Max Activating Token Index: 286

Text #10

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7678. Min Act: -0.1700

Data Index: 8319493 (Open Web Text)

Max Activating Token Index: 881

Text #11

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7536. Min Act: -0.1700

Data Index: 4262675 (Open Web Text)

Max Activating Token Index: 933

Text #12

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.6827. Min Act: -0.1700

Data Index: 4511053 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7394. Min Act: -0.1700

Data Index: 4975402 (Open Web Text)

Max Activating Token Index: 273

Text #14

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7323. Min Act: -0.1700

Data Index: 5958416 (Open Web Text)

Max Activating Token Index: 676

Text #15

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7296. Min Act: -0.1700

Data Index: 6821215 (Open Web Text)

Max Activating Token Index: 721

Text #16

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7062. Min Act: -0.1700

Data Index: 8039612 (Open Web Text)

Max Activating Token Index: 56

Text #17

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7190. Min Act: -0.1700

Data Index: 831567 (Open Web Text)

Max Activating Token Index: 881

Text #18

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7119. Min Act: -0.1700

Data Index: 4740949 (Open Web Text)

Max Activating Token Index: 42

Text #19

Max Range: 4.0339. Min Range: -4.0339

Max Act: 3.7139. Min Act: -0.1700

Data Index: 3418950 (Open Web Text)

Max Activating Token Index: 129