Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 99 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0186. Min Act: -0.0003

Data Index: 263487 (C4 (Web Text))

Max Activating Token Index: 377

Text #1

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0169. Min Act: -0.0003

Data Index: 487285 (C4 (Web Text))

Max Activating Token Index: 646

Text #2

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0141. Min Act: -0.0003

Data Index: 920924 (C4 (Web Text))

Max Activating Token Index: 552

Text #3

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0144. Min Act: -0.0003

Data Index: 309823 (C4 (Web Text))

Max Activating Token Index: 233

Text #4

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0168. Min Act: -0.0003

Data Index: 1076551 (C4 (Web Text))

Max Activating Token Index: 384

Text #5

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0134. Min Act: -0.0003

Data Index: 256928 (C4 (Web Text))

Max Activating Token Index: 522

Text #6

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0159. Min Act: -0.0003

Data Index: 1356931 (C4 (Web Text))

Max Activating Token Index: 297

Text #7

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0156. Min Act: -0.0003

Data Index: 1026070 (C4 (Web Text))

Max Activating Token Index: 525

Text #8

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0164. Min Act: -0.0003

Data Index: 560530 (C4 (Web Text))

Max Activating Token Index: 738

Text #9

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0166. Min Act: -0.0003

Data Index: 1260895 (C4 (Web Text))

Max Activating Token Index: 306

Text #10

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0124. Min Act: -0.0003

Data Index: 431897 (C4 (Web Text))

Max Activating Token Index: 535

Text #11

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0135. Min Act: -0.0003

Data Index: 767207 (C4 (Web Text))

Max Activating Token Index: 88

Text #12

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0136. Min Act: -0.0003

Data Index: 595830 (C4 (Web Text))

Max Activating Token Index: 420

Text #13

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0123. Min Act: -0.0003

Data Index: 826113 (C4 (Web Text))

Max Activating Token Index: 317

Text #14

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0121. Min Act: -0.0004

Data Index: 352699 (C4 (Web Text))

Max Activating Token Index: 537

Text #15

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0156. Min Act: -0.0003

Data Index: 783315 (C4 (Web Text))

Max Activating Token Index: 780

Text #16

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0129. Min Act: -0.0003

Data Index: 1015163 (C4 (Web Text))

Max Activating Token Index: 891

Text #17

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0178. Min Act: -0.0003

Data Index: 342795 (C4 (Web Text))

Max Activating Token Index: 212

Text #18

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0140. Min Act: -0.0003

Data Index: 1208553 (C4 (Web Text))

Max Activating Token Index: 509

Text #19

Max Range: 0.0186. Min Range: -0.0186

Max Act: 0.0137. Min Act: -0.0004

Data Index: 531703 (C4 (Web Text))

Max Activating Token Index: 874