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

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

Neuron 2627 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: 0.0200. Min Range: -0.0200

Max Act: 0.0200. Min Act: -0.0002

Data Index: 377564 (C4 (Web Text))

Max Activating Token Index: 342

Text #1

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0003

Data Index: 699486 (C4 (Web Text))

Max Activating Token Index: 501

Text #2

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0184. Min Act: -0.0003

Data Index: 207715 (C4 (Web Text))

Max Activating Token Index: 419

Text #3

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0180. Min Act: -0.0003

Data Index: 187686 (C4 (Web Text))

Max Activating Token Index: 165

Text #4

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0189. Min Act: -0.0003

Data Index: 692453 (C4 (Web Text))

Max Activating Token Index: 429

Text #5

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0185. Min Act: -0.0003

Data Index: 141371 (C4 (Web Text))

Max Activating Token Index: 375

Text #6

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0171. Min Act: -0.0002

Data Index: 227864 (C4 (Web Text))

Max Activating Token Index: 611

Text #7

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0182. Min Act: -0.0003

Data Index: 216074 (C4 (Web Text))

Max Activating Token Index: 416

Text #8

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0003

Data Index: 1190469 (C4 (Web Text))

Max Activating Token Index: 49

Text #9

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0173. Min Act: -0.0003

Data Index: 47843 (C4 (Web Text))

Max Activating Token Index: 52

Text #10

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1389812 (Python Code)

Max Activating Token Index: 39

Text #11

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1573962 (Python Code)

Max Activating Token Index: 16

Text #12

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0171. Min Act: -0.0003

Data Index: 392982 (C4 (Web Text))

Max Activating Token Index: 613

Text #13

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0167. Min Act: -0.0002

Data Index: 127058 (C4 (Web Text))

Max Activating Token Index: 111

Text #14

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0170. Min Act: -0.0003

Data Index: 201764 (C4 (Web Text))

Max Activating Token Index: 812

Text #15

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0177. Min Act: -0.0003

Data Index: 76149 (C4 (Web Text))

Max Activating Token Index: 210

Text #16

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0168. Min Act: -0.0003

Data Index: 295528 (C4 (Web Text))

Max Activating Token Index: 417

Text #17

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0168. Min Act: -0.0003

Data Index: 205937 (C4 (Web Text))

Max Activating Token Index: 211

Text #18

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0162. Min Act: -0.0003

Data Index: 209700 (C4 (Web Text))

Max Activating Token Index: 215

Text #19

Max Range: 0.0200. Min Range: -0.0200

Max Act: 0.0165. Min Act: -0.0003

Data Index: 819071 (C4 (Web Text))

Max Activating Token Index: 41