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

Dataset: Open Web Text

Neuron 959 in Layer 6

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: 3.5302. Min Range: -3.5302

Max Act: 3.5208. Min Act: -0.1700

Data Index: 7223528 (Open Web Text)

Max Activating Token Index: 585

Text #1

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.5278. Min Act: -0.1700

Data Index: 3069290 (Open Web Text)

Max Activating Token Index: 256

Text #2

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.5302. Min Act: -0.1700

Data Index: 8410257 (Open Web Text)

Max Activating Token Index: 428

Text #3

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.5124. Min Act: -0.1700

Data Index: 7903709 (Open Web Text)

Max Activating Token Index: 703

Text #4

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.5222. Min Act: -0.1700

Data Index: 3939247 (Open Web Text)

Max Activating Token Index: 563

Text #5

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4292. Min Act: -0.1700

Data Index: 5304086 (Open Web Text)

Max Activating Token Index: 617

Text #6

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3966. Min Act: -0.1700

Data Index: 36694 (Open Web Text)

Max Activating Token Index: 257

Text #7

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.4027. Min Act: -0.1700

Data Index: 4325093 (Open Web Text)

Max Activating Token Index: 499

Text #8

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3828. Min Act: -0.1700

Data Index: 349631 (Open Web Text)

Max Activating Token Index: 107

Text #9

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3686. Min Act: -0.1700

Data Index: 7933405 (Open Web Text)

Max Activating Token Index: 440

Text #10

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3639. Min Act: -0.1700

Data Index: 8366902 (Open Web Text)

Max Activating Token Index: 910

Text #11

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3593. Min Act: -0.1700

Data Index: 7332577 (Open Web Text)

Max Activating Token Index: 697

Text #12

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3705. Min Act: -0.1700

Data Index: 2368031 (Open Web Text)

Max Activating Token Index: 868

Text #13

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3414. Min Act: -0.1700

Data Index: 3603779 (Open Web Text)

Max Activating Token Index: 714

Text #14

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3444. Min Act: -0.1700

Data Index: 6445347 (Open Web Text)

Max Activating Token Index: 537

Text #15

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3402. Min Act: -0.1700

Data Index: 7407504 (Open Web Text)

Max Activating Token Index: 389

Text #16

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3351. Min Act: -0.1700

Data Index: 6825938 (Open Web Text)

Max Activating Token Index: 962

Text #17

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3242. Min Act: -0.1700

Data Index: 3642701 (Open Web Text)

Max Activating Token Index: 145

Text #18

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3096. Min Act: -0.1700

Data Index: 8008902 (Open Web Text)

Max Activating Token Index: 812

Text #19

Max Range: 3.5302. Min Range: -3.5302

Max Act: 3.3055. Min Act: -0.1700

Data Index: 7431144 (Open Web Text)

Max Activating Token Index: 288