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

Dataset: Open Web Text

Neuron 773 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: 4.5255. Min Range: -4.5255

Max Act: 4.5255. Min Act: -0.1700

Data Index: 8758381 (Open Web Text)

Max Activating Token Index: 679

Text #1

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4755. Min Act: -0.1700

Data Index: 2340363 (Open Web Text)

Max Activating Token Index: 473

Text #2

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3975. Min Act: -0.1700

Data Index: 3076074 (Open Web Text)

Max Activating Token Index: 980

Text #3

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3812. Min Act: -0.1700

Data Index: 1047899 (Open Web Text)

Max Activating Token Index: 457

Text #4

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.4072. Min Act: -0.1700

Data Index: 4776341 (Open Web Text)

Max Activating Token Index: 197

Text #5

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3791. Min Act: -0.1700

Data Index: 8004365 (Open Web Text)

Max Activating Token Index: 92

Text #6

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3525. Min Act: -0.1700

Data Index: 1186536 (Open Web Text)

Max Activating Token Index: 435

Text #7

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3559. Min Act: -0.1700

Data Index: 347883 (Open Web Text)

Max Activating Token Index: 585

Text #8

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3174. Min Act: -0.1700

Data Index: 8693943 (Open Web Text)

Max Activating Token Index: 383

Text #9

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3858. Min Act: -0.1700

Data Index: 8562623 (Open Web Text)

Max Activating Token Index: 539

Text #10

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3281. Min Act: -0.1700

Data Index: 4631650 (Open Web Text)

Max Activating Token Index: 425

Text #11

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3302. Min Act: -0.1700

Data Index: 4024991 (Open Web Text)

Max Activating Token Index: 165

Text #12

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3167. Min Act: -0.1700

Data Index: 621740 (Open Web Text)

Max Activating Token Index: 290

Text #13

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3321. Min Act: -0.1700

Data Index: 6846876 (Open Web Text)

Max Activating Token Index: 234

Text #14

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3202. Min Act: -0.1700

Data Index: 6806082 (Open Web Text)

Max Activating Token Index: 228

Text #15

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3015. Min Act: -0.1700

Data Index: 5431963 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3176. Min Act: -0.1700

Data Index: 5675856 (Open Web Text)

Max Activating Token Index: 126

Text #17

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3001. Min Act: -0.1700

Data Index: 322247 (Open Web Text)

Max Activating Token Index: 722

Text #18

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.2790. Min Act: -0.1700

Data Index: 1432746 (Open Web Text)

Max Activating Token Index: 343

Text #19

Max Range: 4.5255. Min Range: -4.5255

Max Act: 4.3226. Min Act: -0.1700

Data Index: 986854 (Open Web Text)

Max Activating Token Index: 635