Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2821 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0003

Data Index: 55769 (C4 (Web Text))

Max Activating Token Index: 754

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0195. Min Act: -0.0003

Data Index: 665970 (C4 (Web Text))

Max Activating Token Index: 1021

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0003

Data Index: 185804 (C4 (Web Text))

Max Activating Token Index: 659

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0193. Min Act: -0.0003

Data Index: 469549 (C4 (Web Text))

Max Activating Token Index: 295

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1159447 (C4 (Web Text))

Max Activating Token Index: 65

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0187. Min Act: -0.0003

Data Index: 66509 (C4 (Web Text))

Max Activating Token Index: 762

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1169389 (C4 (Web Text))

Max Activating Token Index: 852

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0186. Min Act: -0.0003

Data Index: 232665 (C4 (Web Text))

Max Activating Token Index: 16

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0172. Min Act: -0.0003

Data Index: 721408 (C4 (Web Text))

Max Activating Token Index: 122

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1013851 (C4 (Web Text))

Max Activating Token Index: 204

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0178. Min Act: -0.0003

Data Index: 247173 (C4 (Web Text))

Max Activating Token Index: 202

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1368 (C4 (Web Text))

Max Activating Token Index: 635

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0180. Min Act: -0.0003

Data Index: 143216 (C4 (Web Text))

Max Activating Token Index: 935

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0172. Min Act: -0.0003

Data Index: 459448 (C4 (Web Text))

Max Activating Token Index: 345

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1162045 (C4 (Web Text))

Max Activating Token Index: 329

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0179. Min Act: -0.0003

Data Index: 554155 (C4 (Web Text))

Max Activating Token Index: 150

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0175. Min Act: -0.0003

Data Index: 232388 (C4 (Web Text))

Max Activating Token Index: 397

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0159. Min Act: -0.0003

Data Index: 563595 (C4 (Web Text))

Max Activating Token Index: 1019

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1166184 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0164. Min Act: -0.0003

Data Index: 793623 (C4 (Web Text))

Max Activating Token Index: 41