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

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

Neuron 3771 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0176. Min Act: -0.0002

Data Index: 740844 (C4 (Web Text))

Max Activating Token Index: 493

Text #1

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1074901 (C4 (Web Text))

Max Activating Token Index: 37

Text #2

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1044366 (C4 (Web Text))

Max Activating Token Index: 196

Text #3

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0170. Min Act: -0.0002

Data Index: 355858 (C4 (Web Text))

Max Activating Token Index: 866

Text #4

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0169. Min Act: -0.0002

Data Index: 620469 (C4 (Web Text))

Max Activating Token Index: 67

Text #5

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0169. Min Act: -0.0002

Data Index: 44965 (C4 (Web Text))

Max Activating Token Index: 261

Text #6

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0169. Min Act: -0.0002

Data Index: 727608 (C4 (Web Text))

Max Activating Token Index: 701

Text #7

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1093871 (C4 (Web Text))

Max Activating Token Index: 210

Text #8

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 211618 (C4 (Web Text))

Max Activating Token Index: 99

Text #9

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1008682 (C4 (Web Text))

Max Activating Token Index: 45

Text #10

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 1022615 (C4 (Web Text))

Max Activating Token Index: 72

Text #11

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 402851 (C4 (Web Text))

Max Activating Token Index: 806

Text #12

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 461055 (C4 (Web Text))

Max Activating Token Index: 108

Text #13

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0168. Min Act: -0.0002

Data Index: 421936 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0170. Min Act: -0.0002

Data Index: 336384 (C4 (Web Text))

Max Activating Token Index: 177

Text #15

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1074779 (C4 (Web Text))

Max Activating Token Index: 532

Text #16

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1258263 (C4 (Web Text))

Max Activating Token Index: 831

Text #17

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1203483 (C4 (Web Text))

Max Activating Token Index: 372

Text #18

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0165. Min Act: -0.0002

Data Index: 576831 (C4 (Web Text))

Max Activating Token Index: 719

Text #19

Max Range: 0.0176. Min Range: -0.0176

Max Act: 0.0165. Min Act: -0.0002

Data Index: 65461 (C4 (Web Text))

Max Activating Token Index: 65