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

Dataset: Open Web Text

Neuron 1074 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: 2.3941. Min Range: -2.3941

Max Act: 2.3913. Min Act: -0.1700

Data Index: 2536655 (Open Web Text)

Max Activating Token Index: 488

Text #1

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3941. Min Act: -0.1700

Data Index: 7056374 (Open Web Text)

Max Activating Token Index: 314

Text #2

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3724. Min Act: -0.1700

Data Index: 5695617 (Open Web Text)

Max Activating Token Index: 585

Text #3

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3780. Min Act: -0.1700

Data Index: 409238 (Open Web Text)

Max Activating Token Index: 624

Text #4

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3329. Min Act: -0.1700

Data Index: 7501291 (Open Web Text)

Max Activating Token Index: 778

Text #5

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3515. Min Act: -0.1700

Data Index: 89447 (Open Web Text)

Max Activating Token Index: 20

Text #6

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3418. Min Act: -0.1700

Data Index: 7229067 (Open Web Text)

Max Activating Token Index: 415

Text #7

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3357. Min Act: -0.1700

Data Index: 7667337 (Open Web Text)

Max Activating Token Index: 369

Text #8

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3312. Min Act: -0.1700

Data Index: 7399378 (Open Web Text)

Max Activating Token Index: 711

Text #9

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3351. Min Act: -0.1700

Data Index: 6712382 (Open Web Text)

Max Activating Token Index: 298

Text #10

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3198. Min Act: -0.1700

Data Index: 7296305 (Open Web Text)

Max Activating Token Index: 25

Text #11

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3189. Min Act: -0.1700

Data Index: 5719601 (Open Web Text)

Max Activating Token Index: 409

Text #12

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3260. Min Act: -0.1700

Data Index: 3531894 (Open Web Text)

Max Activating Token Index: 703

Text #13

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3184. Min Act: -0.1700

Data Index: 1755405 (Open Web Text)

Max Activating Token Index: 21

Text #14

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3181. Min Act: -0.1700

Data Index: 3070984 (Open Web Text)

Max Activating Token Index: 397

Text #15

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3175. Min Act: -0.1700

Data Index: 1856273 (Open Web Text)

Max Activating Token Index: 830

Text #16

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.2832. Min Act: -0.1700

Data Index: 4686334 (Open Web Text)

Max Activating Token Index: 968

Text #17

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3151. Min Act: -0.1700

Data Index: 4897429 (Open Web Text)

Max Activating Token Index: 953

Text #18

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3003. Min Act: -0.1700

Data Index: 2682007 (Open Web Text)

Max Activating Token Index: 619

Text #19

Max Range: 2.3941. Min Range: -2.3941

Max Act: 2.3041. Min Act: -0.1700

Data Index: 481815 (Open Web Text)

Max Activating Token Index: 9