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

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

Neuron 684 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: 0.0195. Min Range: -0.0195

Max Act: 0.0195. Min Act: -0.0002

Data Index: 948308 (C4 (Web Text))

Max Activating Token Index: 356

Text #1

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0194. Min Act: -0.0003

Data Index: 377819 (C4 (Web Text))

Max Activating Token Index: 658

Text #2

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0184. Min Act: -0.0002

Data Index: 1038074 (C4 (Web Text))

Max Activating Token Index: 893

Text #3

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0179. Min Act: -0.0002

Data Index: 1306614 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0171. Min Act: -0.0003

Data Index: 136361 (C4 (Web Text))

Max Activating Token Index: 520

Text #5

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0176. Min Act: -0.0003

Data Index: 288646 (C4 (Web Text))

Max Activating Token Index: 21

Text #6

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0168. Min Act: -0.0003

Data Index: 304986 (C4 (Web Text))

Max Activating Token Index: 309

Text #7

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0002

Data Index: 856747 (C4 (Web Text))

Max Activating Token Index: 451

Text #8

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0156. Min Act: -0.0003

Data Index: 835719 (C4 (Web Text))

Max Activating Token Index: 877

Text #9

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0170. Min Act: -0.0003

Data Index: 242185 (C4 (Web Text))

Max Activating Token Index: 528

Text #10

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0169. Min Act: -0.0003

Data Index: 1328537 (C4 (Web Text))

Max Activating Token Index: 453

Text #11

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0140. Min Act: -0.0002

Data Index: 893306 (C4 (Web Text))

Max Activating Token Index: 649

Text #12

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0163. Min Act: -0.0002

Data Index: 227166 (C4 (Web Text))

Max Activating Token Index: 744

Text #13

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0167. Min Act: -0.0002

Data Index: 348779 (C4 (Web Text))

Max Activating Token Index: 171

Text #14

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0002

Data Index: 956576 (C4 (Web Text))

Max Activating Token Index: 809

Text #15

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0159. Min Act: -0.0002

Data Index: 90362 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0158. Min Act: -0.0003

Data Index: 1333408 (C4 (Web Text))

Max Activating Token Index: 168

Text #17

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0161. Min Act: -0.0002

Data Index: 986548 (C4 (Web Text))

Max Activating Token Index: 377

Text #18

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0152. Min Act: -0.0002

Data Index: 235744 (C4 (Web Text))

Max Activating Token Index: 762

Text #19

Max Range: 0.0195. Min Range: -0.0195

Max Act: 0.0155. Min Act: -0.0003

Data Index: 894510 (C4 (Web Text))

Max Activating Token Index: 506