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

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

Neuron 3370 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: 0.0250. Min Range: -0.0250

Max Act: 0.0250. Min Act: -0.0003

Data Index: 1371461 (Python Code)

Max Activating Token Index: 110

Text #1

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0223. Min Act: -0.0003

Data Index: 657270 (C4 (Web Text))

Max Activating Token Index: 310

Text #2

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1656247 (Python Code)

Max Activating Token Index: 198

Text #3

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0228. Min Act: -0.0002

Data Index: 1422317 (Python Code)

Max Activating Token Index: 219

Text #4

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1270807 (C4 (Web Text))

Max Activating Token Index: 150

Text #5

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0189. Min Act: -0.0003

Data Index: 12633 (C4 (Web Text))

Max Activating Token Index: 220

Text #6

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0188. Min Act: -0.0002

Data Index: 762709 (C4 (Web Text))

Max Activating Token Index: 482

Text #7

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0181. Min Act: -0.0002

Data Index: 866026 (C4 (Web Text))

Max Activating Token Index: 337

Text #8

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0174. Min Act: -0.0002

Data Index: 177028 (C4 (Web Text))

Max Activating Token Index: 689

Text #9

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1209018 (C4 (Web Text))

Max Activating Token Index: 679

Text #10

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0171. Min Act: -0.0003

Data Index: 261695 (C4 (Web Text))

Max Activating Token Index: 22

Text #11

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1302729 (C4 (Web Text))

Max Activating Token Index: 517

Text #12

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0170. Min Act: -0.0003

Data Index: 208405 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0175. Min Act: -0.0002

Data Index: 756385 (C4 (Web Text))

Max Activating Token Index: 821

Text #14

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1649883 (Python Code)

Max Activating Token Index: 231

Text #15

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0164. Min Act: -0.0003

Data Index: 29955 (C4 (Web Text))

Max Activating Token Index: 1011

Text #16

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0180. Min Act: -0.0003

Data Index: 1606902 (Python Code)

Max Activating Token Index: 614

Text #17

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0175. Min Act: -0.0002

Data Index: 8058 (C4 (Web Text))

Max Activating Token Index: 311

Text #18

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0165. Min Act: -0.0003

Data Index: 534943 (C4 (Web Text))

Max Activating Token Index: 413

Text #19

Max Range: 0.0250. Min Range: -0.0250

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1170458 (C4 (Web Text))

Max Activating Token Index: 722