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

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

Neuron 1933 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0149. Min Act: -0.0003

Data Index: 1507853 (Python Code)

Max Activating Token Index: 346

Text #1

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0142. Min Act: -0.0002

Data Index: 1360471 (Python Code)

Max Activating Token Index: 445

Text #2

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1407378 (Python Code)

Max Activating Token Index: 959

Text #3

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0133. Min Act: -0.0002

Data Index: 1398577 (Python Code)

Max Activating Token Index: 789

Text #4

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0003

Data Index: 441080 (C4 (Web Text))

Max Activating Token Index: 30

Text #5

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0114. Min Act: -0.0003

Data Index: 1211761 (C4 (Web Text))

Max Activating Token Index: 664

Text #6

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0112. Min Act: -0.0003

Data Index: 1073346 (C4 (Web Text))

Max Activating Token Index: 82

Text #7

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0111. Min Act: -0.0003

Data Index: 168356 (C4 (Web Text))

Max Activating Token Index: 240

Text #8

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0111. Min Act: -0.0003

Data Index: 301516 (C4 (Web Text))

Max Activating Token Index: 291

Text #9

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0111. Min Act: -0.0003

Data Index: 1281925 (C4 (Web Text))

Max Activating Token Index: 74

Text #10

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0112. Min Act: -0.0003

Data Index: 829702 (C4 (Web Text))

Max Activating Token Index: 213

Text #11

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0110. Min Act: -0.0003

Data Index: 1317294 (C4 (Web Text))

Max Activating Token Index: 527

Text #12

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0110. Min Act: -0.0002

Data Index: 1442507 (Python Code)

Max Activating Token Index: 408

Text #13

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0111. Min Act: -0.0003

Data Index: 563332 (C4 (Web Text))

Max Activating Token Index: 537

Text #14

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0109. Min Act: -0.0003

Data Index: 471774 (C4 (Web Text))

Max Activating Token Index: 164

Text #15

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: -0.0003

Data Index: 500160 (C4 (Web Text))

Max Activating Token Index: 214

Text #16

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: -0.0003

Data Index: 192864 (C4 (Web Text))

Max Activating Token Index: 189

Text #17

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0108. Min Act: -0.0003

Data Index: 1062014 (C4 (Web Text))

Max Activating Token Index: 16

Text #18

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0109. Min Act: -0.0003

Data Index: 1243658 (C4 (Web Text))

Max Activating Token Index: 212

Text #19

Max Range: 0.0149. Min Range: -0.0149

Max Act: 0.0107. Min Act: -0.0003

Data Index: 733144 (C4 (Web Text))

Max Activating Token Index: 557