Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 460 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0303. Min Act: -0.0004

Data Index: 401471 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0201. Min Act: -0.0004

Data Index: 471731 (C4 (Web Text))

Max Activating Token Index: 218

Text #2

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0215. Min Act: -0.0004

Data Index: 513259 (C4 (Web Text))

Max Activating Token Index: 189

Text #3

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0208. Min Act: -0.0004

Data Index: 971014 (C4 (Web Text))

Max Activating Token Index: 69

Text #4

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0192. Min Act: -0.0004

Data Index: 674865 (C4 (Web Text))

Max Activating Token Index: 121

Text #5

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0183. Min Act: -0.0004

Data Index: 1043303 (C4 (Web Text))

Max Activating Token Index: 11

Text #6

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0171. Min Act: -0.0004

Data Index: 479357 (C4 (Web Text))

Max Activating Token Index: 205

Text #7

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0182. Min Act: -0.0004

Data Index: 94259 (C4 (Web Text))

Max Activating Token Index: 241

Text #8

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0164. Min Act: -0.0004

Data Index: 1282316 (C4 (Web Text))

Max Activating Token Index: 861

Text #9

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0174. Min Act: -0.0004

Data Index: 1187072 (C4 (Web Text))

Max Activating Token Index: 728

Text #10

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0174. Min Act: -0.0004

Data Index: 1185639 (C4 (Web Text))

Max Activating Token Index: 734

Text #11

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0181. Min Act: -0.0004

Data Index: 1192330 (C4 (Web Text))

Max Activating Token Index: 86

Text #12

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0169. Min Act: -0.0004

Data Index: 797029 (C4 (Web Text))

Max Activating Token Index: 37

Text #13

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0170. Min Act: -0.0004

Data Index: 852493 (C4 (Web Text))

Max Activating Token Index: 127

Text #14

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0177. Min Act: -0.0004

Data Index: 146182 (C4 (Web Text))

Max Activating Token Index: 715

Text #15

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0171. Min Act: -0.0004

Data Index: 147620 (C4 (Web Text))

Max Activating Token Index: 288

Text #16

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0174. Min Act: -0.0004

Data Index: 1091564 (C4 (Web Text))

Max Activating Token Index: 91

Text #17

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0176. Min Act: -0.0004

Data Index: 986889 (C4 (Web Text))

Max Activating Token Index: 260

Text #18

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0169. Min Act: -0.0004

Data Index: 1048946 (C4 (Web Text))

Max Activating Token Index: 114

Text #19

Max Range: 0.0303. Min Range: -0.0303

Max Act: 0.0169. Min Act: -0.0004

Data Index: 359961 (C4 (Web Text))

Max Activating Token Index: 178