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

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

Neuron 4982 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0308. Min Act: -0.0002

Data Index: 928104 (C4 (Web Text))

Max Activating Token Index: 213

Text #1

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0302. Min Act: -0.0002

Data Index: 482030 (C4 (Web Text))

Max Activating Token Index: 338

Text #2

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0302. Min Act: -0.0002

Data Index: 129718 (C4 (Web Text))

Max Activating Token Index: 458

Text #3

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0302. Min Act: -0.0002

Data Index: 576666 (C4 (Web Text))

Max Activating Token Index: 26

Text #4

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0302. Min Act: -0.0002

Data Index: 1016682 (C4 (Web Text))

Max Activating Token Index: 604

Text #5

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0301. Min Act: -0.0002

Data Index: 1115953 (C4 (Web Text))

Max Activating Token Index: 42

Text #6

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0300. Min Act: -0.0002

Data Index: 713304 (C4 (Web Text))

Max Activating Token Index: 115

Text #7

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0300. Min Act: -0.0002

Data Index: 1307891 (C4 (Web Text))

Max Activating Token Index: 89

Text #8

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0297. Min Act: -0.0002

Data Index: 813739 (C4 (Web Text))

Max Activating Token Index: 68

Text #9

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0297. Min Act: -0.0002

Data Index: 983972 (C4 (Web Text))

Max Activating Token Index: 22

Text #10

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1258428 (C4 (Web Text))

Max Activating Token Index: 55

Text #11

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0296. Min Act: -0.0002

Data Index: 527110 (C4 (Web Text))

Max Activating Token Index: 127

Text #12

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0293. Min Act: -0.0002

Data Index: 1340945 (C4 (Web Text))

Max Activating Token Index: 35

Text #13

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0293. Min Act: -0.0002

Data Index: 205899 (C4 (Web Text))

Max Activating Token Index: 410

Text #14

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0292. Min Act: -0.0002

Data Index: 255497 (C4 (Web Text))

Max Activating Token Index: 884

Text #15

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0292. Min Act: -0.0002

Data Index: 1053483 (C4 (Web Text))

Max Activating Token Index: 66

Text #16

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0291. Min Act: -0.0002

Data Index: 21872 (C4 (Web Text))

Max Activating Token Index: 32

Text #17

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0291. Min Act: -0.0002

Data Index: 796882 (C4 (Web Text))

Max Activating Token Index: 182

Text #18

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0296. Min Act: -0.0002

Data Index: 129917 (C4 (Web Text))

Max Activating Token Index: 130

Text #19

Max Range: 0.0308. Min Range: -0.0308

Max Act: 0.0290. Min Act: -0.0002

Data Index: 168283 (C4 (Web Text))

Max Activating Token Index: 231