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

Dataset: Open Web Text

Neuron 1028 in Layer 3

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: 2.3306. Min Range: -2.3306

Max Act: 2.3267. Min Act: -0.1700

Data Index: 357821 (Open Web Text)

Max Activating Token Index: 942

Text #1

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.3306. Min Act: -0.1700

Data Index: 8730020 (Open Web Text)

Max Activating Token Index: 537

Text #2

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.3016. Min Act: -0.1700

Data Index: 6711712 (Open Web Text)

Max Activating Token Index: 507

Text #3

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2919. Min Act: -0.1700

Data Index: 4307984 (Open Web Text)

Max Activating Token Index: 203

Text #4

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2875. Min Act: -0.1700

Data Index: 3803662 (Open Web Text)

Max Activating Token Index: 419

Text #5

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2741. Min Act: -0.1700

Data Index: 3173551 (Open Web Text)

Max Activating Token Index: 838

Text #6

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2635. Min Act: -0.1700

Data Index: 4226403 (Open Web Text)

Max Activating Token Index: 667

Text #7

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2405. Min Act: -0.1700

Data Index: 7824716 (Open Web Text)

Max Activating Token Index: 527

Text #8

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2612. Min Act: -0.1700

Data Index: 7674367 (Open Web Text)

Max Activating Token Index: 830

Text #9

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2617. Min Act: -0.1700

Data Index: 2962367 (Open Web Text)

Max Activating Token Index: 369

Text #10

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2306. Min Act: -0.1700

Data Index: 2874778 (Open Web Text)

Max Activating Token Index: 792

Text #11

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2382. Min Act: -0.1700

Data Index: 7893593 (Open Web Text)

Max Activating Token Index: 759

Text #12

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2650. Min Act: -0.1700

Data Index: 2942 (Open Web Text)

Max Activating Token Index: 314

Text #13

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2358. Min Act: -0.1700

Data Index: 7313707 (Open Web Text)

Max Activating Token Index: 792

Text #14

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2187. Min Act: -0.1700

Data Index: 1849665 (Open Web Text)

Max Activating Token Index: 292

Text #15

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2155. Min Act: -0.1700

Data Index: 1406356 (Open Web Text)

Max Activating Token Index: 75

Text #16

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2268. Min Act: -0.1700

Data Index: 3695155 (Open Web Text)

Max Activating Token Index: 638

Text #17

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2154. Min Act: -0.1700

Data Index: 1158083 (Open Web Text)

Max Activating Token Index: 957

Text #18

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2233. Min Act: -0.1700

Data Index: 2025342 (Open Web Text)

Max Activating Token Index: 782

Text #19

Max Range: 2.3306. Min Range: -2.3306

Max Act: 2.2050. Min Act: -0.1700

Data Index: 4209824 (Open Web Text)

Max Activating Token Index: 588