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

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

Neuron 4635 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2214. Min Act: -0.0002

Data Index: 198239 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2206. Min Act: -0.0002

Data Index: 846079 (C4 (Web Text))

Max Activating Token Index: 241

Text #2

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2191. Min Act: -0.0003

Data Index: 564814 (C4 (Web Text))

Max Activating Token Index: 376

Text #3

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2228. Min Act: -0.0002

Data Index: 857440 (C4 (Web Text))

Max Activating Token Index: 297

Text #4

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2029. Min Act: -0.0002

Data Index: 104086 (C4 (Web Text))

Max Activating Token Index: 247

Text #5

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2076. Min Act: -0.0002

Data Index: 322268 (C4 (Web Text))

Max Activating Token Index: 54

Text #6

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2065. Min Act: -0.0002

Data Index: 608948 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2144. Min Act: -0.0002

Data Index: 304632 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2066. Min Act: -0.0002

Data Index: 246522 (C4 (Web Text))

Max Activating Token Index: 439

Text #9

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2070. Min Act: -0.0002

Data Index: 1189532 (C4 (Web Text))

Max Activating Token Index: 51

Text #10

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.2018. Min Act: -0.0002

Data Index: 258334 (C4 (Web Text))

Max Activating Token Index: 125

Text #11

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1884. Min Act: -0.0002

Data Index: 1002477 (C4 (Web Text))

Max Activating Token Index: 731

Text #12

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1986. Min Act: -0.0003

Data Index: 183430 (C4 (Web Text))

Max Activating Token Index: 345

Text #13

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1967. Min Act: -0.0003

Data Index: 198974 (C4 (Web Text))

Max Activating Token Index: 754

Text #14

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1904. Min Act: -0.0002

Data Index: 128561 (C4 (Web Text))

Max Activating Token Index: 229

Text #15

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1942. Min Act: -0.0002

Data Index: 1186182 (C4 (Web Text))

Max Activating Token Index: 78

Text #16

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1959. Min Act: -0.0002

Data Index: 970617 (C4 (Web Text))

Max Activating Token Index: 119

Text #17

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1834. Min Act: -0.0002

Data Index: 973552 (C4 (Web Text))

Max Activating Token Index: 197

Text #18

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1949. Min Act: -0.0002

Data Index: 427997 (C4 (Web Text))

Max Activating Token Index: 875

Text #19

Max Range: 0.2228. Min Range: -0.2228

Max Act: 0.1995. Min Act: -0.0002

Data Index: 504872 (C4 (Web Text))

Max Activating Token Index: 314