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

Dataset: Open Web Text

Neuron 1267 in Layer 5

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: 5.5875. Min Range: -5.5875

Max Act: 5.5875. Min Act: -0.1700

Data Index: 7271279 (Open Web Text)

Max Activating Token Index: 798

Text #1

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.5531. Min Act: -0.1700

Data Index: 4366483 (Open Web Text)

Max Activating Token Index: 859

Text #2

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.5099. Min Act: -0.1700

Data Index: 8032629 (Open Web Text)

Max Activating Token Index: 995

Text #3

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4737. Min Act: -0.1700

Data Index: 6628087 (Open Web Text)

Max Activating Token Index: 523

Text #4

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4531. Min Act: -0.1700

Data Index: 5070929 (Open Web Text)

Max Activating Token Index: 909

Text #5

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4679. Min Act: -0.1700

Data Index: 7085855 (Open Web Text)

Max Activating Token Index: 343

Text #6

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4407. Min Act: -0.1700

Data Index: 7978372 (Open Web Text)

Max Activating Token Index: 548

Text #7

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4237. Min Act: -0.1700

Data Index: 8815085 (Open Web Text)

Max Activating Token Index: 945

Text #8

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3592. Min Act: -0.1700

Data Index: 4730813 (Open Web Text)

Max Activating Token Index: 728

Text #9

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4183. Min Act: -0.1700

Data Index: 7634225 (Open Web Text)

Max Activating Token Index: 335

Text #10

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.4089. Min Act: -0.1700

Data Index: 3089170 (Open Web Text)

Max Activating Token Index: 752

Text #11

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3763. Min Act: -0.1700

Data Index: 3573747 (Open Web Text)

Max Activating Token Index: 264

Text #12

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3494. Min Act: -0.1700

Data Index: 6545868 (Open Web Text)

Max Activating Token Index: 163

Text #13

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3532. Min Act: -0.1700

Data Index: 1578569 (Open Web Text)

Max Activating Token Index: 375

Text #14

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3470. Min Act: -0.1700

Data Index: 1760348 (Open Web Text)

Max Activating Token Index: 787

Text #15

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3343. Min Act: -0.1700

Data Index: 1960175 (Open Web Text)

Max Activating Token Index: 58

Text #16

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3277. Min Act: -0.1700

Data Index: 198512 (Open Web Text)

Max Activating Token Index: 52

Text #17

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3224. Min Act: -0.1700

Data Index: 881761 (Open Web Text)

Max Activating Token Index: 861

Text #18

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3262. Min Act: -0.1700

Data Index: 8037165 (Open Web Text)

Max Activating Token Index: 239

Text #19

Max Range: 5.5875. Min Range: -5.5875

Max Act: 5.3335. Min Act: -0.1700

Data Index: 5205558 (Open Web Text)

Max Activating Token Index: 564