Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1457 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0176. Min Act: -0.0005

Data Index: 750668 (C4 (Web Text))

Max Activating Token Index: 349

Text #1

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0178. Min Act: -0.0005

Data Index: 245904 (C4 (Web Text))

Max Activating Token Index: 592

Text #2

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0174. Min Act: -0.0005

Data Index: 990275 (C4 (Web Text))

Max Activating Token Index: 463

Text #3

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0175. Min Act: -0.0005

Data Index: 606237 (C4 (Web Text))

Max Activating Token Index: 30

Text #4

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0166. Min Act: -0.0005

Data Index: 461895 (C4 (Web Text))

Max Activating Token Index: 418

Text #5

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0165. Min Act: -0.0005

Data Index: 182576 (C4 (Web Text))

Max Activating Token Index: 93

Text #6

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0162. Min Act: -0.0005

Data Index: 1214871 (C4 (Web Text))

Max Activating Token Index: 66

Text #7

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0165. Min Act: -0.0005

Data Index: 524190 (C4 (Web Text))

Max Activating Token Index: 454

Text #8

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0160. Min Act: -0.0005

Data Index: 206965 (C4 (Web Text))

Max Activating Token Index: 163

Text #9

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0005

Data Index: 411446 (C4 (Web Text))

Max Activating Token Index: 471

Text #10

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0158. Min Act: -0.0005

Data Index: 626906 (C4 (Web Text))

Max Activating Token Index: 221

Text #11

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0005

Data Index: 469010 (C4 (Web Text))

Max Activating Token Index: 823

Text #12

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0005

Data Index: 914970 (C4 (Web Text))

Max Activating Token Index: 336

Text #13

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0156. Min Act: -0.0005

Data Index: 179557 (C4 (Web Text))

Max Activating Token Index: 603

Text #14

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0159. Min Act: -0.0005

Data Index: 168257 (C4 (Web Text))

Max Activating Token Index: 707

Text #15

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0005

Data Index: 865900 (C4 (Web Text))

Max Activating Token Index: 292

Text #16

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0155. Min Act: -0.0005

Data Index: 513418 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0005

Data Index: 129751 (C4 (Web Text))

Max Activating Token Index: 368

Text #18

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0154. Min Act: -0.0005

Data Index: 875784 (C4 (Web Text))

Max Activating Token Index: 32

Text #19

Max Range: 0.0178. Min Range: -0.0178

Max Act: 0.0151. Min Act: -0.0005

Data Index: 217625 (C4 (Web Text))

Max Activating Token Index: 1023