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

Dataset: Open Web Text

Neuron 2721 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: 3.4307. Min Range: -3.4307

Max Act: 3.4307. Min Act: -0.1700

Data Index: 8221472 (Open Web Text)

Max Activating Token Index: 924

Text #1

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.4138. Min Act: -0.1700

Data Index: 6137804 (Open Web Text)

Max Activating Token Index: 222

Text #2

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3889. Min Act: -0.1700

Data Index: 7283147 (Open Web Text)

Max Activating Token Index: 406

Text #3

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.4020. Min Act: -0.1700

Data Index: 1775351 (Open Web Text)

Max Activating Token Index: 313

Text #4

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3718. Min Act: -0.1700

Data Index: 8379056 (Open Web Text)

Max Activating Token Index: 726

Text #5

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3490. Min Act: -0.1700

Data Index: 2452657 (Open Web Text)

Max Activating Token Index: 2

Text #6

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3490. Min Act: -0.1700

Data Index: 7798129 (Open Web Text)

Max Activating Token Index: 2

Text #7

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3679. Min Act: -0.1700

Data Index: 1082151 (Open Web Text)

Max Activating Token Index: 956

Text #8

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3326. Min Act: -0.1700

Data Index: 3857107 (Open Web Text)

Max Activating Token Index: 661

Text #9

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3769. Min Act: -0.1700

Data Index: 447565 (Open Web Text)

Max Activating Token Index: 623

Text #10

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3448. Min Act: -0.1700

Data Index: 8139018 (Open Web Text)

Max Activating Token Index: 343

Text #11

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3339. Min Act: -0.1700

Data Index: 8753289 (Open Web Text)

Max Activating Token Index: 354

Text #12

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3490. Min Act: -0.1700

Data Index: 8048452 (Open Web Text)

Max Activating Token Index: 2

Text #13

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3630. Min Act: -0.1700

Data Index: 1132692 (Open Web Text)

Max Activating Token Index: 122

Text #14

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3308. Min Act: -0.1700

Data Index: 8175190 (Open Web Text)

Max Activating Token Index: 934

Text #15

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3408. Min Act: -0.1700

Data Index: 4284091 (Open Web Text)

Max Activating Token Index: 518

Text #16

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3242. Min Act: -0.1700

Data Index: 8425015 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3486. Min Act: -0.1700

Data Index: 3666222 (Open Web Text)

Max Activating Token Index: 1015

Text #18

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3189. Min Act: -0.1700

Data Index: 4113308 (Open Web Text)

Max Activating Token Index: 804

Text #19

Max Range: 3.4307. Min Range: -3.4307

Max Act: 3.3055. Min Act: -0.1700

Data Index: 7076906 (Open Web Text)

Max Activating Token Index: 3