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

Dataset: Open Web Text

Neuron 55 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: 4.4218. Min Range: -4.4218

Max Act: 4.4218. Min Act: -0.1700

Data Index: 3510182 (Open Web Text)

Max Activating Token Index: 514

Text #1

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.3452. Min Act: -0.1700

Data Index: 4818779 (Open Web Text)

Max Activating Token Index: 184

Text #2

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.3524. Min Act: -0.1700

Data Index: 7469240 (Open Web Text)

Max Activating Token Index: 89

Text #3

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.2833. Min Act: -0.1700

Data Index: 4361780 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.2040. Min Act: -0.1700

Data Index: 2911287 (Open Web Text)

Max Activating Token Index: 679

Text #5

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1597. Min Act: -0.1700

Data Index: 6548331 (Open Web Text)

Max Activating Token Index: 195

Text #6

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1675. Min Act: -0.1700

Data Index: 8724715 (Open Web Text)

Max Activating Token Index: 177

Text #7

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1909. Min Act: -0.1700

Data Index: 6159453 (Open Web Text)

Max Activating Token Index: 466

Text #8

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1176. Min Act: -0.1700

Data Index: 5545806 (Open Web Text)

Max Activating Token Index: 581

Text #9

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1623. Min Act: -0.1700

Data Index: 6402841 (Open Web Text)

Max Activating Token Index: 551

Text #10

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1259. Min Act: -0.1700

Data Index: 4671926 (Open Web Text)

Max Activating Token Index: 885

Text #11

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0875. Min Act: -0.1700

Data Index: 5639657 (Open Web Text)

Max Activating Token Index: 114

Text #12

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.1128. Min Act: -0.1700

Data Index: 892002 (Open Web Text)

Max Activating Token Index: 431

Text #13

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0419. Min Act: -0.1700

Data Index: 1101032 (Open Web Text)

Max Activating Token Index: 789

Text #14

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0943. Min Act: -0.1700

Data Index: 4145955 (Open Web Text)

Max Activating Token Index: 80

Text #15

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0485. Min Act: -0.1700

Data Index: 2935376 (Open Web Text)

Max Activating Token Index: 200

Text #16

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0625. Min Act: -0.1700

Data Index: 627978 (Open Web Text)

Max Activating Token Index: 615

Text #17

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0345. Min Act: -0.1700

Data Index: 4902207 (Open Web Text)

Max Activating Token Index: 949

Text #18

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0495. Min Act: -0.1700

Data Index: 2274794 (Open Web Text)

Max Activating Token Index: 914

Text #19

Max Range: 4.4218. Min Range: -4.4218

Max Act: 4.0373. Min Act: -0.1700

Data Index: 3324440 (Open Web Text)

Max Activating Token Index: 961