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

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

Neuron 2000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0001

Data Index: 380713 (C4 (Web Text))

Max Activating Token Index: 378

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0231. Min Act: -0.0001

Data Index: 386967 (C4 (Web Text))

Max Activating Token Index: 93

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0220. Min Act: -0.0001

Data Index: 26905 (C4 (Web Text))

Max Activating Token Index: 801

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0208. Min Act: -0.0002

Data Index: 412937 (C4 (Web Text))

Max Activating Token Index: 38

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0210. Min Act: -0.0002

Data Index: 454955 (C4 (Web Text))

Max Activating Token Index: 220

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0212. Min Act: -0.0001

Data Index: 737870 (C4 (Web Text))

Max Activating Token Index: 196

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0210. Min Act: -0.0002

Data Index: 727789 (C4 (Web Text))

Max Activating Token Index: 233

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0188. Min Act: -0.0002

Data Index: 824520 (C4 (Web Text))

Max Activating Token Index: 910

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0196. Min Act: -0.0002

Data Index: 300786 (C4 (Web Text))

Max Activating Token Index: 19

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0190. Min Act: -0.0002

Data Index: 492491 (C4 (Web Text))

Max Activating Token Index: 195

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0173. Min Act: -0.0001

Data Index: 655337 (C4 (Web Text))

Max Activating Token Index: 1022

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0177. Min Act: -0.0001

Data Index: 662081 (C4 (Web Text))

Max Activating Token Index: 119

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0176. Min Act: -0.0001

Data Index: 230340 (C4 (Web Text))

Max Activating Token Index: 376

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0185. Min Act: -0.0001

Data Index: 199170 (C4 (Web Text))

Max Activating Token Index: 668

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0170. Min Act: -0.0001

Data Index: 98149 (C4 (Web Text))

Max Activating Token Index: 377

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0166. Min Act: -0.0002

Data Index: 528684 (C4 (Web Text))

Max Activating Token Index: 745

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0170. Min Act: -0.0002

Data Index: 124077 (C4 (Web Text))

Max Activating Token Index: 938

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0173. Min Act: -0.0001

Data Index: 296849 (C4 (Web Text))

Max Activating Token Index: 917

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0173. Min Act: -0.0001

Data Index: 362531 (C4 (Web Text))

Max Activating Token Index: 58

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0172. Min Act: -0.0001

Data Index: 209499 (C4 (Web Text))

Max Activating Token Index: 355