Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3576 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0192. Min Act: -0.0002

Data Index: 1217948 (C4 (Web Text))

Max Activating Token Index: 318

Text #1

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0186. Min Act: -0.0002

Data Index: 931446 (C4 (Web Text))

Max Activating Token Index: 740

Text #2

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0188. Min Act: -0.0003

Data Index: 526489 (C4 (Web Text))

Max Activating Token Index: 751

Text #3

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1593442 (Python Code)

Max Activating Token Index: 204

Text #4

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0183. Min Act: -0.0003

Data Index: 694062 (C4 (Web Text))

Max Activating Token Index: 297

Text #5

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0182. Min Act: -0.0003

Data Index: 221341 (C4 (Web Text))

Max Activating Token Index: 275

Text #6

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0181. Min Act: -0.0002

Data Index: 1199561 (C4 (Web Text))

Max Activating Token Index: 795

Text #7

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1548462 (Python Code)

Max Activating Token Index: 246

Text #8

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0179. Min Act: -0.0002

Data Index: 523377 (C4 (Web Text))

Max Activating Token Index: 123

Text #9

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0176. Min Act: -0.0003

Data Index: 568458 (C4 (Web Text))

Max Activating Token Index: 339

Text #10

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0175. Min Act: -0.0003

Data Index: 731903 (C4 (Web Text))

Max Activating Token Index: 121

Text #11

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0175. Min Act: -0.0002

Data Index: 889090 (C4 (Web Text))

Max Activating Token Index: 141

Text #12

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0002

Data Index: 1163879 (C4 (Web Text))

Max Activating Token Index: 631

Text #13

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0178. Min Act: -0.0002

Data Index: 528060 (C4 (Web Text))

Max Activating Token Index: 213

Text #14

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0174. Min Act: -0.0003

Data Index: 471225 (C4 (Web Text))

Max Activating Token Index: 168

Text #15

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0173. Min Act: -0.0002

Data Index: 1514422 (Python Code)

Max Activating Token Index: 59

Text #16

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0172. Min Act: -0.0002

Data Index: 1575635 (Python Code)

Max Activating Token Index: 31

Text #17

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0172. Min Act: -0.0003

Data Index: 739067 (C4 (Web Text))

Max Activating Token Index: 310

Text #18

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0171. Min Act: -0.0002

Data Index: 1258919 (C4 (Web Text))

Max Activating Token Index: 104

Text #19

Max Range: 0.0192. Min Range: -0.0192

Max Act: 0.0172. Min Act: -0.0003

Data Index: 852552 (C4 (Web Text))

Max Activating Token Index: 807