Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2034 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0006

Data Index: 683877 (C4 (Web Text))

Max Activating Token Index: 593

Text #1

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0183. Min Act: -0.0006

Data Index: 146444 (C4 (Web Text))

Max Activating Token Index: 133

Text #2

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0181. Min Act: -0.0006

Data Index: 832505 (C4 (Web Text))

Max Activating Token Index: 889

Text #3

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0176. Min Act: -0.0006

Data Index: 878948 (C4 (Web Text))

Max Activating Token Index: 479

Text #4

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0175. Min Act: -0.0006

Data Index: 781642 (C4 (Web Text))

Max Activating Token Index: 637

Text #5

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0167. Min Act: -0.0006

Data Index: 501687 (C4 (Web Text))

Max Activating Token Index: 774

Text #6

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0172. Min Act: -0.0006

Data Index: 1247769 (C4 (Web Text))

Max Activating Token Index: 467

Text #7

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0171. Min Act: -0.0006

Data Index: 964837 (C4 (Web Text))

Max Activating Token Index: 996

Text #8

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0165. Min Act: -0.0006

Data Index: 1196828 (C4 (Web Text))

Max Activating Token Index: 988

Text #9

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0165. Min Act: -0.0006

Data Index: 668852 (C4 (Web Text))

Max Activating Token Index: 521

Text #10

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0164. Min Act: -0.0006

Data Index: 519542 (C4 (Web Text))

Max Activating Token Index: 53

Text #11

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0163. Min Act: -0.0006

Data Index: 4693 (C4 (Web Text))

Max Activating Token Index: 754

Text #12

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0166. Min Act: -0.0006

Data Index: 649370 (C4 (Web Text))

Max Activating Token Index: 993

Text #13

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0162. Min Act: -0.0006

Data Index: 1052668 (C4 (Web Text))

Max Activating Token Index: 289

Text #14

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0161. Min Act: -0.0006

Data Index: 75637 (C4 (Web Text))

Max Activating Token Index: 336

Text #15

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0160. Min Act: -0.0006

Data Index: 1034334 (C4 (Web Text))

Max Activating Token Index: 505

Text #16

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0155. Min Act: -0.0006

Data Index: 1551851 (Python Code)

Max Activating Token Index: 1023

Text #17

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1213074 (C4 (Web Text))

Max Activating Token Index: 968

Text #18

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0158. Min Act: -0.0006

Data Index: 788256 (C4 (Web Text))

Max Activating Token Index: 708

Text #19

Max Range: 0.0183. Min Range: -0.0183

Max Act: 0.0159. Min Act: -0.0006

Data Index: 1037424 (C4 (Web Text))

Max Activating Token Index: 745