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

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

Neuron 395 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: 1.1306. Min Range: -1.1306

Max Act: 1.1306. Min Act: -0.0003

Data Index: 892769 (C4 (Web Text))

Max Activating Token Index: 32

Text #1

Max Range: 1.1306. Min Range: -1.1306

Max Act: 1.1036. Min Act: -0.0003

Data Index: 1243009 (C4 (Web Text))

Max Activating Token Index: 677

Text #2

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.9749. Min Act: -0.0002

Data Index: 707276 (C4 (Web Text))

Max Activating Token Index: 357

Text #3

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.8943. Min Act: -0.0003

Data Index: 322969 (C4 (Web Text))

Max Activating Token Index: 432

Text #4

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.8770. Min Act: -0.0003

Data Index: 891465 (C4 (Web Text))

Max Activating Token Index: 80

Text #5

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.8485. Min Act: -0.0002

Data Index: 1329413 (C4 (Web Text))

Max Activating Token Index: 201

Text #6

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.8171. Min Act: -0.0002

Data Index: 597072 (C4 (Web Text))

Max Activating Token Index: 35

Text #7

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.8180. Min Act: -0.0003

Data Index: 1230515 (C4 (Web Text))

Max Activating Token Index: 91

Text #8

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7917. Min Act: -0.0003

Data Index: 952255 (C4 (Web Text))

Max Activating Token Index: 94

Text #9

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7886. Min Act: -0.0002

Data Index: 836247 (C4 (Web Text))

Max Activating Token Index: 595

Text #10

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7805. Min Act: -0.0003

Data Index: 153738 (C4 (Web Text))

Max Activating Token Index: 192

Text #11

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7733. Min Act: -0.0003

Data Index: 872721 (C4 (Web Text))

Max Activating Token Index: 185

Text #12

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7589. Min Act: -0.0003

Data Index: 1201313 (C4 (Web Text))

Max Activating Token Index: 66

Text #13

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7414. Min Act: -0.0002

Data Index: 1343447 (C4 (Web Text))

Max Activating Token Index: 79

Text #14

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7273. Min Act: -0.0003

Data Index: 389292 (C4 (Web Text))

Max Activating Token Index: 575

Text #15

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7181. Min Act: -0.0003

Data Index: 449886 (C4 (Web Text))

Max Activating Token Index: 34

Text #16

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7534. Min Act: -0.0003

Data Index: 462925 (C4 (Web Text))

Max Activating Token Index: 125

Text #17

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7086. Min Act: -0.0003

Data Index: 618912 (C4 (Web Text))

Max Activating Token Index: 210

Text #18

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7136. Min Act: -0.0003

Data Index: 896805 (C4 (Web Text))

Max Activating Token Index: 419

Text #19

Max Range: 1.1306. Min Range: -1.1306

Max Act: 0.7085. Min Act: -0.0003

Data Index: 1137224 (C4 (Web Text))

Max Activating Token Index: 483