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

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

Neuron 1292 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1262302 (C4 (Web Text))

Max Activating Token Index: 601

Text #1

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0172. Min Act: -0.0002

Data Index: 745085 (C4 (Web Text))

Max Activating Token Index: 20

Text #2

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0153. Min Act: -0.0003

Data Index: 1183234 (C4 (Web Text))

Max Activating Token Index: 78

Text #3

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0152. Min Act: -0.0003

Data Index: 116059 (C4 (Web Text))

Max Activating Token Index: 740

Text #4

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0144. Min Act: -0.0003

Data Index: 723276 (C4 (Web Text))

Max Activating Token Index: 61

Text #5

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1576141 (Python Code)

Max Activating Token Index: 31

Text #6

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1175050 (C4 (Web Text))

Max Activating Token Index: 59

Text #7

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0140. Min Act: -0.0003

Data Index: 541840 (C4 (Web Text))

Max Activating Token Index: 180

Text #8

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0165. Min Act: -0.0002

Data Index: 753119 (C4 (Web Text))

Max Activating Token Index: 276

Text #9

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0168. Min Act: -0.0003

Data Index: 697099 (C4 (Web Text))

Max Activating Token Index: 190

Text #10

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0157. Min Act: -0.0003

Data Index: 326582 (C4 (Web Text))

Max Activating Token Index: 274

Text #11

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0154. Min Act: -0.0003

Data Index: 581374 (C4 (Web Text))

Max Activating Token Index: 386

Text #12

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0147. Min Act: -0.0003

Data Index: 109249 (C4 (Web Text))

Max Activating Token Index: 431

Text #13

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0157. Min Act: -0.0003

Data Index: 1178446 (C4 (Web Text))

Max Activating Token Index: 357

Text #14

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0158. Min Act: -0.0003

Data Index: 823917 (C4 (Web Text))

Max Activating Token Index: 28

Text #15

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0154. Min Act: -0.0003

Data Index: 34329 (C4 (Web Text))

Max Activating Token Index: 390

Text #16

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0151. Min Act: -0.0002

Data Index: 75818 (C4 (Web Text))

Max Activating Token Index: 87

Text #17

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0156. Min Act: -0.0003

Data Index: 855380 (C4 (Web Text))

Max Activating Token Index: 928

Text #18

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0170. Min Act: -0.0003

Data Index: 322736 (C4 (Web Text))

Max Activating Token Index: 207

Text #19

Max Range: 0.0177. Min Range: -0.0177

Max Act: 0.0141. Min Act: -0.0002

Data Index: 121292 (C4 (Web Text))

Max Activating Token Index: 498