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

Dataset: Open Web Text

Neuron 529 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: 1.6482. Min Range: -1.6482

Max Act: 1.6482. Min Act: -0.1700

Data Index: 1270220 (Open Web Text)

Max Activating Token Index: 178

Text #1

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6309. Min Act: -0.1700

Data Index: 3499921 (Open Web Text)

Max Activating Token Index: 133

Text #2

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6250. Min Act: -0.1699

Data Index: 7196341 (Open Web Text)

Max Activating Token Index: 194

Text #3

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6315. Min Act: -0.1694

Data Index: 3898573 (Open Web Text)

Max Activating Token Index: 534

Text #4

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6250. Min Act: -0.1700

Data Index: 34290 (Open Web Text)

Max Activating Token Index: 961

Text #5

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6155. Min Act: -0.1700

Data Index: 549917 (Open Web Text)

Max Activating Token Index: 315

Text #6

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6174. Min Act: -0.1700

Data Index: 782581 (Open Web Text)

Max Activating Token Index: 361

Text #7

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6120. Min Act: -0.1700

Data Index: 4578398 (Open Web Text)

Max Activating Token Index: 934

Text #8

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6152. Min Act: -0.1699

Data Index: 4610350 (Open Web Text)

Max Activating Token Index: 403

Text #9

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6063. Min Act: -0.1700

Data Index: 8249065 (Open Web Text)

Max Activating Token Index: 163

Text #10

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6082. Min Act: -0.1700

Data Index: 1119688 (Open Web Text)

Max Activating Token Index: 408

Text #11

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6048. Min Act: -0.1700

Data Index: 6713646 (Open Web Text)

Max Activating Token Index: 374

Text #12

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6042. Min Act: -0.1700

Data Index: 5412662 (Open Web Text)

Max Activating Token Index: 547

Text #13

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6136. Min Act: -0.1700

Data Index: 5886523 (Open Web Text)

Max Activating Token Index: 161

Text #14

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.5969. Min Act: -0.1700

Data Index: 3473518 (Open Web Text)

Max Activating Token Index: 604

Text #15

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.5975. Min Act: -0.1697

Data Index: 5233151 (Open Web Text)

Max Activating Token Index: 134

Text #16

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.5959. Min Act: -0.1700

Data Index: 5306013 (Open Web Text)

Max Activating Token Index: 361

Text #17

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.5990. Min Act: -0.1699

Data Index: 2117857 (Open Web Text)

Max Activating Token Index: 329

Text #18

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.6035. Min Act: -0.1700

Data Index: 5484008 (Open Web Text)

Max Activating Token Index: 276

Text #19

Max Range: 1.6482. Min Range: -1.6482

Max Act: 1.5961. Min Act: -0.1699

Data Index: 5934984 (Open Web Text)

Max Activating Token Index: 544