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

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

Neuron 2585 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0196. Min Act: -0.0003

Data Index: 647110 (C4 (Web Text))

Max Activating Token Index: 983

Text #1

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0185. Min Act: -0.0004

Data Index: 275218 (C4 (Web Text))

Max Activating Token Index: 68

Text #2

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0181. Min Act: -0.0003

Data Index: 142298 (C4 (Web Text))

Max Activating Token Index: 964

Text #3

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0179. Min Act: -0.0004

Data Index: 621720 (C4 (Web Text))

Max Activating Token Index: 78

Text #4

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0176. Min Act: -0.0004

Data Index: 121191 (C4 (Web Text))

Max Activating Token Index: 800

Text #5

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0175. Min Act: -0.0004

Data Index: 213706 (C4 (Web Text))

Max Activating Token Index: 345

Text #6

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0174. Min Act: -0.0004

Data Index: 455403 (C4 (Web Text))

Max Activating Token Index: 165

Text #7

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0177. Min Act: -0.0004

Data Index: 263687 (C4 (Web Text))

Max Activating Token Index: 575

Text #8

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0173. Min Act: -0.0004

Data Index: 312474 (C4 (Web Text))

Max Activating Token Index: 182

Text #9

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0172. Min Act: -0.0004

Data Index: 744252 (C4 (Web Text))

Max Activating Token Index: 284

Text #10

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0171. Min Act: -0.0003

Data Index: 221782 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0003

Data Index: 85355 (C4 (Web Text))

Max Activating Token Index: 291

Text #12

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1306784 (C4 (Web Text))

Max Activating Token Index: 303

Text #13

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0003

Data Index: 44250 (C4 (Web Text))

Max Activating Token Index: 239

Text #14

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0169. Min Act: -0.0004

Data Index: 647347 (C4 (Web Text))

Max Activating Token Index: 256

Text #15

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0165. Min Act: -0.0004

Data Index: 1228510 (C4 (Web Text))

Max Activating Token Index: 346

Text #16

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0003

Data Index: 514567 (C4 (Web Text))

Max Activating Token Index: 533

Text #17

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0004

Data Index: 953437 (C4 (Web Text))

Max Activating Token Index: 595

Text #18

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1139168 (C4 (Web Text))

Max Activating Token Index: 159

Text #19

Max Range: 0.0196. Min Range: -0.0196

Max Act: 0.0167. Min Act: -0.0004

Data Index: 599953 (C4 (Web Text))

Max Activating Token Index: 159