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

Dataset: Open Web Text

Neuron 1039 in Layer 1

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: 1.5457. Min Range: -1.5457

Max Act: 1.5457. Min Act: -0.1700

Data Index: 8651507 (Open Web Text)

Max Activating Token Index: 669

Text #1

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5336. Min Act: -0.1700

Data Index: 7500068 (Open Web Text)

Max Activating Token Index: 816

Text #2

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5290. Min Act: -0.1700

Data Index: 2580345 (Open Web Text)

Max Activating Token Index: 676

Text #3

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5350. Min Act: -0.1700

Data Index: 7621343 (Open Web Text)

Max Activating Token Index: 562

Text #4

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.5003. Min Act: -0.1700

Data Index: 2939935 (Open Web Text)

Max Activating Token Index: 715

Text #5

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4969. Min Act: -0.1699

Data Index: 7605211 (Open Web Text)

Max Activating Token Index: 152

Text #6

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4928. Min Act: -0.1700

Data Index: 4742959 (Open Web Text)

Max Activating Token Index: 1023

Text #7

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4863. Min Act: -0.1700

Data Index: 7471810 (Open Web Text)

Max Activating Token Index: 300

Text #8

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4792. Min Act: -0.1700

Data Index: 8624362 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4721. Min Act: -0.1700

Data Index: 1208209 (Open Web Text)

Max Activating Token Index: 395

Text #10

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4559. Min Act: -0.1700

Data Index: 5793034 (Open Web Text)

Max Activating Token Index: 757

Text #11

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4451. Min Act: -0.1700

Data Index: 4885700 (Open Web Text)

Max Activating Token Index: 940

Text #12

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4331. Min Act: -0.1700

Data Index: 5920924 (Open Web Text)

Max Activating Token Index: 85

Text #13

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4306. Min Act: -0.1700

Data Index: 1372941 (Open Web Text)

Max Activating Token Index: 172

Text #14

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4279. Min Act: -0.1700

Data Index: 4698995 (Open Web Text)

Max Activating Token Index: 775

Text #15

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4266. Min Act: -0.1700

Data Index: 4388400 (Open Web Text)

Max Activating Token Index: 616

Text #16

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4198. Min Act: -0.1700

Data Index: 8177111 (Open Web Text)

Max Activating Token Index: 956

Text #17

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4164. Min Act: -0.1699

Data Index: 2715610 (Open Web Text)

Max Activating Token Index: 472

Text #18

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4238. Min Act: -0.1700

Data Index: 4413762 (Open Web Text)

Max Activating Token Index: 540

Text #19

Max Range: 1.5457. Min Range: -1.5457

Max Act: 1.4193. Min Act: -0.1700

Data Index: 6677382 (Open Web Text)

Max Activating Token Index: 176