Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 5265 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0251. Min Act: -0.0000

Data Index: 846822 (C4 (Web Text))

Max Activating Token Index: 127

Text #1

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0250. Min Act: -0.0000

Data Index: 367857 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0209. Min Act: -0.0000

Data Index: 1138377 (C4 (Web Text))

Max Activating Token Index: 188

Text #3

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0192. Min Act: -0.0000

Data Index: 155746 (C4 (Web Text))

Max Activating Token Index: 235

Text #4

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0161. Min Act: -0.0000

Data Index: 1481521 (Python Code)

Max Activating Token Index: 168

Text #5

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0155. Min Act: -0.0000

Data Index: 1127776 (C4 (Web Text))

Max Activating Token Index: 71

Text #6

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0161. Min Act: -0.0000

Data Index: 451051 (C4 (Web Text))

Max Activating Token Index: 130

Text #7

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0155. Min Act: -0.0000

Data Index: 916588 (C4 (Web Text))

Max Activating Token Index: 93

Text #8

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0151. Min Act: -0.0000

Data Index: 1508068 (Python Code)

Max Activating Token Index: 244

Text #9

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0170. Min Act: -0.0000

Data Index: 128845 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0162. Min Act: -0.0000

Data Index: 1515846 (Python Code)

Max Activating Token Index: 359

Text #11

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0155. Min Act: -0.0000

Data Index: 1422781 (Python Code)

Max Activating Token Index: 145

Text #12

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0158. Min Act: -0.0000

Data Index: 1572441 (Python Code)

Max Activating Token Index: 149

Text #13

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0152. Min Act: -0.0000

Data Index: 174406 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0156. Min Act: -0.0000

Data Index: 1630063 (Python Code)

Max Activating Token Index: 697

Text #15

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0145. Min Act: -0.0000

Data Index: 1645836 (Python Code)

Max Activating Token Index: 481

Text #16

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1372308 (Python Code)

Max Activating Token Index: 131

Text #17

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0144. Min Act: -0.0000

Data Index: 1471322 (Python Code)

Max Activating Token Index: 250

Text #18

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0149. Min Act: -0.0000

Data Index: 1419495 (Python Code)

Max Activating Token Index: 563

Text #19

Max Range: 0.0251. Min Range: -0.0251

Max Act: 0.0135. Min Act: -0.0000

Data Index: 1552079 (Python Code)

Max Activating Token Index: 280