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

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

Neuron 620 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: 0.0235. Min Range: -0.0235

Max Act: 0.0235. Min Act: -0.0003

Data Index: 1119480 (C4 (Web Text))

Max Activating Token Index: 926

Text #1

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0226. Min Act: -0.0003

Data Index: 1565329 (Python Code)

Max Activating Token Index: 80

Text #2

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1082871 (C4 (Web Text))

Max Activating Token Index: 909

Text #3

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0192. Min Act: -0.0003

Data Index: 687308 (C4 (Web Text))

Max Activating Token Index: 991

Text #4

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0162. Min Act: -0.0003

Data Index: 1038388 (C4 (Web Text))

Max Activating Token Index: 822

Text #5

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0148. Min Act: -0.0003

Data Index: 988449 (C4 (Web Text))

Max Activating Token Index: 737

Text #6

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0180. Min Act: -0.0003

Data Index: 453452 (C4 (Web Text))

Max Activating Token Index: 16

Text #7

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0161. Min Act: -0.0003

Data Index: 456798 (C4 (Web Text))

Max Activating Token Index: 766

Text #8

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0176. Min Act: -0.0003

Data Index: 1128299 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0160. Min Act: -0.0003

Data Index: 677530 (C4 (Web Text))

Max Activating Token Index: 897

Text #10

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0163. Min Act: -0.0003

Data Index: 1294609 (C4 (Web Text))

Max Activating Token Index: 520

Text #11

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0165. Min Act: -0.0003

Data Index: 804798 (C4 (Web Text))

Max Activating Token Index: 829

Text #12

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0161. Min Act: -0.0003

Data Index: 432985 (C4 (Web Text))

Max Activating Token Index: 430

Text #13

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0160. Min Act: -0.0003

Data Index: 1305356 (C4 (Web Text))

Max Activating Token Index: 280

Text #14

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0146. Min Act: -0.0003

Data Index: 338721 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0124. Min Act: -0.0003

Data Index: 1318565 (C4 (Web Text))

Max Activating Token Index: 503

Text #16

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0152. Min Act: -0.0003

Data Index: 876183 (C4 (Web Text))

Max Activating Token Index: 411

Text #17

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0151. Min Act: -0.0003

Data Index: 45508 (C4 (Web Text))

Max Activating Token Index: 38

Text #18

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0147. Min Act: -0.0003

Data Index: 737639 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.0235. Min Range: -0.0235

Max Act: 0.0153. Min Act: -0.0003

Data Index: 781897 (C4 (Web Text))

Max Activating Token Index: 120