Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 739 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0001

Data Index: 1216291 (C4 (Web Text))

Max Activating Token Index: 868

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0212. Min Act: -0.0001

Data Index: 466462 (C4 (Web Text))

Max Activating Token Index: 34

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0186. Min Act: -0.0001

Data Index: 713422 (C4 (Web Text))

Max Activating Token Index: 908

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0195. Min Act: -0.0001

Data Index: 331787 (C4 (Web Text))

Max Activating Token Index: 217

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0181. Min Act: -0.0001

Data Index: 38326 (C4 (Web Text))

Max Activating Token Index: 39

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0180. Min Act: -0.0001

Data Index: 983016 (C4 (Web Text))

Max Activating Token Index: 316

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0184. Min Act: -0.0000

Data Index: 402101 (C4 (Web Text))

Max Activating Token Index: 335

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0163. Min Act: -0.0001

Data Index: 759495 (C4 (Web Text))

Max Activating Token Index: 932

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0165. Min Act: -0.0001

Data Index: 623617 (C4 (Web Text))

Max Activating Token Index: 41

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0169. Min Act: 0.0000

Data Index: 1292209 (C4 (Web Text))

Max Activating Token Index: 588

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0166. Min Act: -0.0001

Data Index: 1138462 (C4 (Web Text))

Max Activating Token Index: 696

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0161. Min Act: -0.0001

Data Index: 1152171 (C4 (Web Text))

Max Activating Token Index: 393

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0157. Min Act: -0.0001

Data Index: 1070378 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0158. Min Act: -0.0001

Data Index: 497509 (C4 (Web Text))

Max Activating Token Index: 21

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0157. Min Act: -0.0001

Data Index: 577475 (C4 (Web Text))

Max Activating Token Index: 12

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0156. Min Act: -0.0001

Data Index: 1231857 (C4 (Web Text))

Max Activating Token Index: 635

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0151. Min Act: -0.0001

Data Index: 1335465 (C4 (Web Text))

Max Activating Token Index: 893

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0157. Min Act: -0.0001

Data Index: 987822 (C4 (Web Text))

Max Activating Token Index: 77

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0159. Min Act: -0.0001

Data Index: 325251 (C4 (Web Text))

Max Activating Token Index: 247

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0147. Min Act: -0.0000

Data Index: 685011 (C4 (Web Text))

Max Activating Token Index: 70