Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3324 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0244. Min Act: -0.0000

Data Index: 879739 (C4 (Web Text))

Max Activating Token Index: 335

Text #1

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0235. Min Act: -0.0000

Data Index: 212215 (C4 (Web Text))

Max Activating Token Index: 390

Text #2

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0235. Min Act: -0.0000

Data Index: 1607987 (Python Code)

Max Activating Token Index: 113

Text #3

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0219. Min Act: -0.0000

Data Index: 578818 (C4 (Web Text))

Max Activating Token Index: 429

Text #4

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0211. Min Act: -0.0000

Data Index: 283007 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0198. Min Act: -0.0000

Data Index: 305981 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0198. Min Act: -0.0000

Data Index: 1117271 (C4 (Web Text))

Max Activating Token Index: 862

Text #7

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0194. Min Act: -0.0000

Data Index: 1590792 (Python Code)

Max Activating Token Index: 780

Text #8

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0186. Min Act: -0.0000

Data Index: 1236911 (C4 (Web Text))

Max Activating Token Index: 240

Text #9

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0194. Min Act: -0.0000

Data Index: 118645 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0192. Min Act: -0.0000

Data Index: 996144 (C4 (Web Text))

Max Activating Token Index: 586

Text #11

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0183. Min Act: -0.0000

Data Index: 639560 (C4 (Web Text))

Max Activating Token Index: 544

Text #12

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0188. Min Act: -0.0000

Data Index: 1569490 (Python Code)

Max Activating Token Index: 197

Text #13

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0187. Min Act: -0.0000

Data Index: 506984 (C4 (Web Text))

Max Activating Token Index: 235

Text #14

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0185. Min Act: -0.0000

Data Index: 1527590 (Python Code)

Max Activating Token Index: 146

Text #15

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0183. Min Act: -0.0000

Data Index: 1042301 (C4 (Web Text))

Max Activating Token Index: 847

Text #16

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0182. Min Act: -0.0000

Data Index: 1642449 (Python Code)

Max Activating Token Index: 389

Text #17

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0186. Min Act: -0.0000

Data Index: 66254 (C4 (Web Text))

Max Activating Token Index: 136

Text #18

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0168. Min Act: -0.0000

Data Index: 1319382 (C4 (Web Text))

Max Activating Token Index: 175

Text #19

Max Range: 0.0244. Min Range: -0.0244

Max Act: 0.0177. Min Act: -0.0000

Data Index: 5984 (C4 (Web Text))

Max Activating Token Index: 448