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

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

Neuron 2321 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: 0.0212. Min Range: -0.0212

Max Act: 0.0210. Min Act: -0.0002

Data Index: 594723 (C4 (Web Text))

Max Activating Token Index: 864

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0203. Min Act: -0.0002

Data Index: 520253 (C4 (Web Text))

Max Activating Token Index: 920

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0212. Min Act: -0.0003

Data Index: 356185 (C4 (Web Text))

Max Activating Token Index: 130

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0183. Min Act: -0.0002

Data Index: 1090887 (C4 (Web Text))

Max Activating Token Index: 502

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0185. Min Act: -0.0003

Data Index: 447210 (C4 (Web Text))

Max Activating Token Index: 648

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0170. Min Act: -0.0003

Data Index: 356176 (C4 (Web Text))

Max Activating Token Index: 641

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0179. Min Act: -0.0003

Data Index: 1360437 (Python Code)

Max Activating Token Index: 391

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1623588 (Python Code)

Max Activating Token Index: 839

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0164. Min Act: -0.0002

Data Index: 537925 (C4 (Web Text))

Max Activating Token Index: 114

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0164. Min Act: -0.0003

Data Index: 1104531 (C4 (Web Text))

Max Activating Token Index: 544

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1261410 (C4 (Web Text))

Max Activating Token Index: 428

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0164. Min Act: -0.0002

Data Index: 193481 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0158. Min Act: -0.0002

Data Index: 686240 (C4 (Web Text))

Max Activating Token Index: 80

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0159. Min Act: -0.0002

Data Index: 674932 (C4 (Web Text))

Max Activating Token Index: 1014

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0156. Min Act: -0.0003

Data Index: 30939 (C4 (Web Text))

Max Activating Token Index: 464

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0155. Min Act: -0.0003

Data Index: 1277337 (C4 (Web Text))

Max Activating Token Index: 950

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0158. Min Act: -0.0002

Data Index: 172925 (C4 (Web Text))

Max Activating Token Index: 437

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0150. Min Act: -0.0003

Data Index: 227930 (C4 (Web Text))

Max Activating Token Index: 489

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0153. Min Act: -0.0002

Data Index: 262105 (C4 (Web Text))

Max Activating Token Index: 1007

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0150. Min Act: -0.0003

Data Index: 1205510 (C4 (Web Text))

Max Activating Token Index: 323