Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1976 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0231. Min Act: -0.0002

Data Index: 1505406 (Python Code)

Max Activating Token Index: 1023

Text #1

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0197. Min Act: -0.0004

Data Index: 449646 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0195. Min Act: -0.0004

Data Index: 1415452 (Python Code)

Max Activating Token Index: 668

Text #3

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0192. Min Act: -0.0003

Data Index: 1643779 (Python Code)

Max Activating Token Index: 630

Text #4

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0185. Min Act: -0.0004

Data Index: 513833 (C4 (Web Text))

Max Activating Token Index: 1023

Text #5

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0185. Min Act: -0.0004

Data Index: 751239 (C4 (Web Text))

Max Activating Token Index: 681

Text #6

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0183. Min Act: -0.0004

Data Index: 448763 (C4 (Web Text))

Max Activating Token Index: 595

Text #7

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0187. Min Act: -0.0004

Data Index: 1237146 (C4 (Web Text))

Max Activating Token Index: 1006

Text #8

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0183. Min Act: -0.0003

Data Index: 1602874 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0004

Data Index: 119164 (C4 (Web Text))

Max Activating Token Index: 196

Text #10

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0177. Min Act: -0.0004

Data Index: 1633326 (Python Code)

Max Activating Token Index: 1023

Text #11

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0176. Min Act: -0.0004

Data Index: 720230 (C4 (Web Text))

Max Activating Token Index: 414

Text #12

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0175. Min Act: -0.0004

Data Index: 133720 (C4 (Web Text))

Max Activating Token Index: 201

Text #13

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0178. Min Act: -0.0004

Data Index: 1075346 (C4 (Web Text))

Max Activating Token Index: 956

Text #14

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1070919 (C4 (Web Text))

Max Activating Token Index: 421

Text #15

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0171. Min Act: -0.0004

Data Index: 299019 (C4 (Web Text))

Max Activating Token Index: 1023

Text #16

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0167. Min Act: -0.0002

Data Index: 1387655 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0175. Min Act: -0.0004

Data Index: 965654 (C4 (Web Text))

Max Activating Token Index: 234

Text #18

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1492672 (Python Code)

Max Activating Token Index: 872

Text #19

Max Range: 0.0231. Min Range: -0.0231

Max Act: 0.0173. Min Act: -0.0004

Data Index: 1255791 (C4 (Web Text))

Max Activating Token Index: 360