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

Dataset: Open Web Text

Neuron 393 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: 3.9964. Min Range: -3.9964

Max Act: 3.9964. Min Act: -0.1700

Data Index: 3219894 (Open Web Text)

Max Activating Token Index: 875

Text #1

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.9027. Min Act: -0.1700

Data Index: 4275602 (Open Web Text)

Max Activating Token Index: 998

Text #2

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.9177. Min Act: -0.1700

Data Index: 2833601 (Open Web Text)

Max Activating Token Index: 788

Text #3

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8731. Min Act: -0.1700

Data Index: 3198810 (Open Web Text)

Max Activating Token Index: 406

Text #4

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8909. Min Act: -0.1700

Data Index: 2031326 (Open Web Text)

Max Activating Token Index: 1020

Text #5

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8813. Min Act: -0.1700

Data Index: 3435725 (Open Web Text)

Max Activating Token Index: 1015

Text #6

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8852. Min Act: -0.1700

Data Index: 8561922 (Open Web Text)

Max Activating Token Index: 27

Text #7

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.9033. Min Act: -0.1700

Data Index: 5547179 (Open Web Text)

Max Activating Token Index: 1012

Text #8

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8857. Min Act: -0.1700

Data Index: 5705292 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8891. Min Act: -0.1700

Data Index: 7075052 (Open Web Text)

Max Activating Token Index: 4

Text #10

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8501. Min Act: -0.1700

Data Index: 538809 (Open Web Text)

Max Activating Token Index: 530

Text #11

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8414. Min Act: -0.1700

Data Index: 3133794 (Open Web Text)

Max Activating Token Index: 507

Text #12

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8333. Min Act: -0.1700

Data Index: 1337609 (Open Web Text)

Max Activating Token Index: 733

Text #13

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8468. Min Act: -0.1700

Data Index: 8551368 (Open Web Text)

Max Activating Token Index: 490

Text #14

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8400. Min Act: -0.1700

Data Index: 1528854 (Open Web Text)

Max Activating Token Index: 990

Text #15

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8432. Min Act: -0.1700

Data Index: 5158482 (Open Web Text)

Max Activating Token Index: 324

Text #16

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8448. Min Act: -0.1700

Data Index: 2151423 (Open Web Text)

Max Activating Token Index: 215

Text #17

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8392. Min Act: -0.1700

Data Index: 4270814 (Open Web Text)

Max Activating Token Index: 961

Text #18

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8359. Min Act: -0.1700

Data Index: 4225804 (Open Web Text)

Max Activating Token Index: 1022

Text #19

Max Range: 3.9964. Min Range: -3.9964

Max Act: 3.8134. Min Act: -0.1700

Data Index: 1498108 (Open Web Text)

Max Activating Token Index: 557