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

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

Neuron 3866 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: 0.0332. Min Range: -0.0332

Max Act: 0.0332. Min Act: -0.0002

Data Index: 928224 (C4 (Web Text))

Max Activating Token Index: 149

Text #1

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0282. Min Act: -0.0002

Data Index: 120114 (C4 (Web Text))

Max Activating Token Index: 19

Text #2

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0266. Min Act: -0.0002

Data Index: 892482 (C4 (Web Text))

Max Activating Token Index: 809

Text #3

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1047507 (C4 (Web Text))

Max Activating Token Index: 478

Text #4

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1511979 (Python Code)

Max Activating Token Index: 111

Text #5

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0244. Min Act: -0.0002

Data Index: 1440895 (Python Code)

Max Activating Token Index: 33

Text #6

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0239. Min Act: -0.0002

Data Index: 760720 (C4 (Web Text))

Max Activating Token Index: 693

Text #7

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0235. Min Act: -0.0002

Data Index: 1627001 (Python Code)

Max Activating Token Index: 762

Text #8

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0230. Min Act: -0.0002

Data Index: 276994 (C4 (Web Text))

Max Activating Token Index: 107

Text #9

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0222. Min Act: -0.0002

Data Index: 507533 (C4 (Web Text))

Max Activating Token Index: 861

Text #10

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1566830 (Python Code)

Max Activating Token Index: 59

Text #11

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1444680 (Python Code)

Max Activating Token Index: 11

Text #12

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0209. Min Act: -0.0002

Data Index: 1534624 (Python Code)

Max Activating Token Index: 28

Text #13

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0208. Min Act: -0.0002

Data Index: 623422 (C4 (Web Text))

Max Activating Token Index: 234

Text #14

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0212. Min Act: -0.0002

Data Index: 194829 (C4 (Web Text))

Max Activating Token Index: 147

Text #15

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0207. Min Act: -0.0002

Data Index: 1632493 (Python Code)

Max Activating Token Index: 10

Text #16

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0203. Min Act: -0.0002

Data Index: 585315 (C4 (Web Text))

Max Activating Token Index: 822

Text #17

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0203. Min Act: -0.0002

Data Index: 82153 (C4 (Web Text))

Max Activating Token Index: 411

Text #18

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0207. Min Act: -0.0002

Data Index: 883863 (C4 (Web Text))

Max Activating Token Index: 50

Text #19

Max Range: 0.0332. Min Range: -0.0332

Max Act: 0.0203. Min Act: -0.0002

Data Index: 133876 (C4 (Web Text))

Max Activating Token Index: 717