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

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

Neuron 882 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: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0002

Data Index: 1117417 (C4 (Web Text))

Max Activating Token Index: 168

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0184. Min Act: -0.0002

Data Index: 421109 (C4 (Web Text))

Max Activating Token Index: 11

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 1324211 (C4 (Web Text))

Max Activating Token Index: 7

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0002

Data Index: 823712 (C4 (Web Text))

Max Activating Token Index: 116

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0178. Min Act: -0.0002

Data Index: 487553 (C4 (Web Text))

Max Activating Token Index: 123

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0002

Data Index: 274446 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0002

Data Index: 130438 (C4 (Web Text))

Max Activating Token Index: 200

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0170. Min Act: -0.0002

Data Index: 638949 (C4 (Web Text))

Max Activating Token Index: 430

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1100831 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0164. Min Act: -0.0002

Data Index: 1091222 (C4 (Web Text))

Max Activating Token Index: 835

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0166. Min Act: -0.0002

Data Index: 1262449 (C4 (Web Text))

Max Activating Token Index: 45

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0002

Data Index: 1053989 (C4 (Web Text))

Max Activating Token Index: 104

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0164. Min Act: -0.0002

Data Index: 367844 (C4 (Web Text))

Max Activating Token Index: 143

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0163. Min Act: -0.0002

Data Index: 1039650 (C4 (Web Text))

Max Activating Token Index: 294

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0162. Min Act: -0.0002

Data Index: 201946 (C4 (Web Text))

Max Activating Token Index: 571

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0162. Min Act: -0.0002

Data Index: 346084 (C4 (Web Text))

Max Activating Token Index: 145

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0159. Min Act: -0.0002

Data Index: 459754 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0156. Min Act: -0.0002

Data Index: 249233 (C4 (Web Text))

Max Activating Token Index: 121

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0157. Min Act: -0.0002

Data Index: 203705 (C4 (Web Text))

Max Activating Token Index: 182

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0156. Min Act: -0.0002

Data Index: 1069371 (C4 (Web Text))

Max Activating Token Index: 356