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

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

Neuron 5098 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: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0002

Data Index: 562680 (C4 (Web Text))

Max Activating Token Index: 338

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0213. Min Act: -0.0002

Data Index: 1537284 (Python Code)

Max Activating Token Index: 375

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0203. Min Act: -0.0002

Data Index: 1160679 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0202. Min Act: -0.0002

Data Index: 669628 (C4 (Web Text))

Max Activating Token Index: 82

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0200. Min Act: -0.0002

Data Index: 778626 (C4 (Web Text))

Max Activating Token Index: 886

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0180. Min Act: -0.0002

Data Index: 828210 (C4 (Web Text))

Max Activating Token Index: 147

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0186. Min Act: -0.0002

Data Index: 990457 (C4 (Web Text))

Max Activating Token Index: 422

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0180. Min Act: -0.0002

Data Index: 505924 (C4 (Web Text))

Max Activating Token Index: 248

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0194. Min Act: -0.0002

Data Index: 580789 (C4 (Web Text))

Max Activating Token Index: 507

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0189. Min Act: -0.0002

Data Index: 688644 (C4 (Web Text))

Max Activating Token Index: 367

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0186. Min Act: -0.0002

Data Index: 95540 (C4 (Web Text))

Max Activating Token Index: 533

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0002

Data Index: 73077 (C4 (Web Text))

Max Activating Token Index: 507

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1059640 (C4 (Web Text))

Max Activating Token Index: 138

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0188. Min Act: -0.0002

Data Index: 1569317 (Python Code)

Max Activating Token Index: 148

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0180. Min Act: -0.0002

Data Index: 1093542 (C4 (Web Text))

Max Activating Token Index: 148

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0176. Min Act: -0.0002

Data Index: 126228 (C4 (Web Text))

Max Activating Token Index: 345

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0175. Min Act: -0.0002

Data Index: 1526925 (Python Code)

Max Activating Token Index: 214

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0172. Min Act: -0.0002

Data Index: 220080 (C4 (Web Text))

Max Activating Token Index: 231

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0169. Min Act: -0.0002

Data Index: 1496194 (Python Code)

Max Activating Token Index: 138

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0002

Data Index: 887693 (C4 (Web Text))

Max Activating Token Index: 118