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

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

Neuron 3129 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: 0.0212. Min Act: -0.0003

Data Index: 1132 (C4 (Web Text))

Max Activating Token Index: 196

Text #1

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0211. Min Act: -0.0003

Data Index: 1553662 (Python Code)

Max Activating Token Index: 593

Text #2

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0199. Min Act: -0.0003

Data Index: 598704 (C4 (Web Text))

Max Activating Token Index: 247

Text #3

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0178. Min Act: -0.0002

Data Index: 823319 (C4 (Web Text))

Max Activating Token Index: 795

Text #4

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0175. Min Act: -0.0003

Data Index: 1512177 (Python Code)

Max Activating Token Index: 592

Text #5

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0165. Min Act: -0.0003

Data Index: 1033349 (C4 (Web Text))

Max Activating Token Index: 205

Text #6

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1078518 (C4 (Web Text))

Max Activating Token Index: 311

Text #7

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0155. Min Act: -0.0002

Data Index: 1652374 (Python Code)

Max Activating Token Index: 346

Text #8

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0157. Min Act: -0.0002

Data Index: 1251031 (C4 (Web Text))

Max Activating Token Index: 806

Text #9

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0153. Min Act: -0.0002

Data Index: 721520 (C4 (Web Text))

Max Activating Token Index: 359

Text #10

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0142. Min Act: -0.0003

Data Index: 1628880 (Python Code)

Max Activating Token Index: 192

Text #11

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0152. Min Act: -0.0003

Data Index: 1484444 (Python Code)

Max Activating Token Index: 588

Text #12

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0150. Min Act: -0.0003

Data Index: 950169 (C4 (Web Text))

Max Activating Token Index: 697

Text #13

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0144. Min Act: -0.0003

Data Index: 453795 (C4 (Web Text))

Max Activating Token Index: 805

Text #14

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0149. Min Act: -0.0003

Data Index: 903589 (C4 (Web Text))

Max Activating Token Index: 382

Text #15

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0145. Min Act: -0.0002

Data Index: 698149 (C4 (Web Text))

Max Activating Token Index: 393

Text #16

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0144. Min Act: -0.0003

Data Index: 491157 (C4 (Web Text))

Max Activating Token Index: 97

Text #17

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0146. Min Act: -0.0003

Data Index: 243676 (C4 (Web Text))

Max Activating Token Index: 893

Text #18

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0143. Min Act: -0.0003

Data Index: 315626 (C4 (Web Text))

Max Activating Token Index: 242

Text #19

Max Range: 0.0212. Min Range: -0.0212

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1064679 (C4 (Web Text))

Max Activating Token Index: 144