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

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

Neuron 1997 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0191. Min Act: -0.0002

Data Index: 277683 (C4 (Web Text))

Max Activating Token Index: 806

Text #1

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0195. Min Act: -0.0002

Data Index: 948452 (C4 (Web Text))

Max Activating Token Index: 326

Text #2

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0189. Min Act: -0.0002

Data Index: 1415697 (Python Code)

Max Activating Token Index: 522

Text #3

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0130. Min Act: -0.0003

Data Index: 693667 (C4 (Web Text))

Max Activating Token Index: 234

Text #4

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0151. Min Act: -0.0002

Data Index: 896876 (C4 (Web Text))

Max Activating Token Index: 214

Text #5

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0150. Min Act: -0.0002

Data Index: 299621 (C4 (Web Text))

Max Activating Token Index: 927

Text #6

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0228. Min Act: -0.0002

Data Index: 775034 (C4 (Web Text))

Max Activating Token Index: 981

Text #7

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0188. Min Act: -0.0002

Data Index: 23132 (C4 (Web Text))

Max Activating Token Index: 151

Text #8

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0144. Min Act: -0.0002

Data Index: 216898 (C4 (Web Text))

Max Activating Token Index: 148

Text #9

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0210. Min Act: -0.0002

Data Index: 377803 (C4 (Web Text))

Max Activating Token Index: 1022

Text #10

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0181. Min Act: -0.0002

Data Index: 564775 (C4 (Web Text))

Max Activating Token Index: 40

Text #11

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0170. Min Act: -0.0002

Data Index: 1223359 (C4 (Web Text))

Max Activating Token Index: 661

Text #12

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0204. Min Act: -0.0002

Data Index: 1637470 (Python Code)

Max Activating Token Index: 327

Text #13

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0184. Min Act: -0.0002

Data Index: 947842 (C4 (Web Text))

Max Activating Token Index: 160

Text #14

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0146. Min Act: -0.0002

Data Index: 1243076 (C4 (Web Text))

Max Activating Token Index: 198

Text #15

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0189. Min Act: -0.0002

Data Index: 390896 (C4 (Web Text))

Max Activating Token Index: 715

Text #16

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0256. Min Act: -0.0002

Data Index: 84906 (C4 (Web Text))

Max Activating Token Index: 262

Text #17

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0182. Min Act: -0.0002

Data Index: 562582 (C4 (Web Text))

Max Activating Token Index: 452

Text #18

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0158. Min Act: -0.0002

Data Index: 152981 (C4 (Web Text))

Max Activating Token Index: 118

Text #19

Max Range: 0.0256. Min Range: -0.0256

Max Act: 0.0214. Min Act: -0.0002

Data Index: 1326295 (C4 (Web Text))

Max Activating Token Index: 432