Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 419 in Layer 11

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 7.1216. Min Range: -7.1216

Max Act: 7.1216. Min Act: -0.0000

Data Index: 359452 (C4 (Web Text))

Max Activating Token Index: 116

Text #1

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9779. Min Act: -0.0000

Data Index: 789520 (C4 (Web Text))

Max Activating Token Index: 514

Text #2

Max Range: 7.1216. Min Range: -7.1216

Max Act: 7.0010. Min Act: -0.0000

Data Index: 734406 (C4 (Web Text))

Max Activating Token Index: 74

Text #3

Max Range: 7.1216. Min Range: -7.1216

Max Act: 7.1166. Min Act: -0.0000

Data Index: 976477 (C4 (Web Text))

Max Activating Token Index: 180

Text #4

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.6675. Min Act: -0.0000

Data Index: 913855 (C4 (Web Text))

Max Activating Token Index: 137

Text #5

Max Range: 7.1216. Min Range: -7.1216

Max Act: 7.0120. Min Act: -0.0000

Data Index: 524019 (C4 (Web Text))

Max Activating Token Index: 195

Text #6

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.9156. Min Act: -0.0000

Data Index: 808656 (C4 (Web Text))

Max Activating Token Index: 781

Text #7

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.6977. Min Act: -0.0000

Data Index: 1129440 (C4 (Web Text))

Max Activating Token Index: 399

Text #8

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.4920. Min Act: -0.0000

Data Index: 950928 (C4 (Web Text))

Max Activating Token Index: 435

Text #9

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.6524. Min Act: -0.0000

Data Index: 424037 (C4 (Web Text))

Max Activating Token Index: 385

Text #10

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.3872. Min Act: -0.0000

Data Index: 422841 (C4 (Web Text))

Max Activating Token Index: 171

Text #11

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.4002. Min Act: -0.0000

Data Index: 760531 (C4 (Web Text))

Max Activating Token Index: 743

Text #12

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.5310. Min Act: -0.0000

Data Index: 1241618 (C4 (Web Text))

Max Activating Token Index: 944

Text #13

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.4854. Min Act: -0.0000

Data Index: 128956 (C4 (Web Text))

Max Activating Token Index: 1003

Text #14

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.0881. Min Act: -0.0000

Data Index: 419638 (C4 (Web Text))

Max Activating Token Index: 796

Text #15

Max Range: 7.1216. Min Range: -7.1216

Max Act: 5.8526. Min Act: -0.0000

Data Index: 809749 (C4 (Web Text))

Max Activating Token Index: 193

Text #16

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.0323. Min Act: -0.0000

Data Index: 1061330 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.1928. Min Act: -0.0000

Data Index: 406215 (C4 (Web Text))

Max Activating Token Index: 800

Text #18

Max Range: 7.1216. Min Range: -7.1216

Max Act: 5.8855. Min Act: -0.0000

Data Index: 746715 (C4 (Web Text))

Max Activating Token Index: 780

Text #19

Max Range: 7.1216. Min Range: -7.1216

Max Act: 6.5141. Min Act: -0.0000

Data Index: 415501 (C4 (Web Text))

Max Activating Token Index: 856