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

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

Neuron 4673 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: 0.0223. Min Range: -0.0223

Max Act: 0.0223. Min Act: -0.0003

Data Index: 555360 (C4 (Web Text))

Max Activating Token Index: 570

Text #1

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0209. Min Act: -0.0003

Data Index: 367737 (C4 (Web Text))

Max Activating Token Index: 35

Text #2

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0174. Min Act: -0.0003

Data Index: 1083549 (C4 (Web Text))

Max Activating Token Index: 264

Text #3

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0170. Min Act: -0.0003

Data Index: 1016607 (C4 (Web Text))

Max Activating Token Index: 755

Text #4

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0158. Min Act: -0.0003

Data Index: 902881 (C4 (Web Text))

Max Activating Token Index: 313

Text #5

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0139. Min Act: -0.0003

Data Index: 185812 (C4 (Web Text))

Max Activating Token Index: 156

Text #6

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0131. Min Act: -0.0003

Data Index: 143240 (C4 (Web Text))

Max Activating Token Index: 569

Text #7

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0124. Min Act: -0.0002

Data Index: 1234881 (C4 (Web Text))

Max Activating Token Index: 287

Text #8

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0125. Min Act: -0.0003

Data Index: 103963 (C4 (Web Text))

Max Activating Token Index: 735

Text #9

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0122. Min Act: -0.0003

Data Index: 438802 (C4 (Web Text))

Max Activating Token Index: 117

Text #10

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0128. Min Act: -0.0003

Data Index: 932438 (C4 (Web Text))

Max Activating Token Index: 276

Text #11

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0123. Min Act: -0.0003

Data Index: 1638100 (Python Code)

Max Activating Token Index: 355

Text #12

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0121. Min Act: -0.0003

Data Index: 360966 (C4 (Web Text))

Max Activating Token Index: 627

Text #13

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0122. Min Act: -0.0003

Data Index: 1155167 (C4 (Web Text))

Max Activating Token Index: 890

Text #14

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0119. Min Act: -0.0003

Data Index: 324507 (C4 (Web Text))

Max Activating Token Index: 471

Text #15

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0120. Min Act: -0.0003

Data Index: 298769 (C4 (Web Text))

Max Activating Token Index: 59

Text #16

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0115. Min Act: -0.0002

Data Index: 235764 (C4 (Web Text))

Max Activating Token Index: 838

Text #17

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0114. Min Act: -0.0003

Data Index: 195202 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0108. Min Act: -0.0003

Data Index: 669030 (C4 (Web Text))

Max Activating Token Index: 76

Text #19

Max Range: 0.0223. Min Range: -0.0223

Max Act: 0.0110. Min Act: -0.0003

Data Index: 613945 (C4 (Web Text))

Max Activating Token Index: 376