Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 36 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0175. Min Act: -0.0006

Data Index: 973696 (C4 (Web Text))

Max Activating Token Index: 844

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0006

Data Index: 1252111 (C4 (Web Text))

Max Activating Token Index: 662

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0179. Min Act: -0.0006

Data Index: 209986 (C4 (Web Text))

Max Activating Token Index: 244

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1133234 (C4 (Web Text))

Max Activating Token Index: 266

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0176. Min Act: -0.0005

Data Index: 1256616 (C4 (Web Text))

Max Activating Token Index: 139

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0179. Min Act: -0.0006

Data Index: 1033104 (C4 (Web Text))

Max Activating Token Index: 131

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0174. Min Act: -0.0006

Data Index: 297030 (C4 (Web Text))

Max Activating Token Index: 302

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0176. Min Act: -0.0006

Data Index: 1217551 (C4 (Web Text))

Max Activating Token Index: 656

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0176. Min Act: -0.0006

Data Index: 195101 (C4 (Web Text))

Max Activating Token Index: 139

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0177. Min Act: -0.0006

Data Index: 152753 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0176. Min Act: -0.0006

Data Index: 325045 (C4 (Web Text))

Max Activating Token Index: 756

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0173. Min Act: -0.0006

Data Index: 272896 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0172. Min Act: -0.0006

Data Index: 54391 (C4 (Web Text))

Max Activating Token Index: 77

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0171. Min Act: -0.0006

Data Index: 1179645 (C4 (Web Text))

Max Activating Token Index: 250

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0170. Min Act: -0.0006

Data Index: 285083 (C4 (Web Text))

Max Activating Token Index: 125

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0166. Min Act: -0.0006

Data Index: 171855 (C4 (Web Text))

Max Activating Token Index: 217

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0165. Min Act: -0.0006

Data Index: 790142 (C4 (Web Text))

Max Activating Token Index: 405

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0168. Min Act: -0.0006

Data Index: 669532 (C4 (Web Text))

Max Activating Token Index: 785

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0168. Min Act: -0.0006

Data Index: 681274 (C4 (Web Text))

Max Activating Token Index: 985

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0173. Min Act: -0.0006

Data Index: 1145192 (C4 (Web Text))

Max Activating Token Index: 847