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

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

Neuron 4044 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: 0.0306. Min Range: -0.0306

Max Act: 0.0306. Min Act: -0.0002

Data Index: 756856 (C4 (Web Text))

Max Activating Token Index: 752

Text #1

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0301. Min Act: -0.0002

Data Index: 113694 (C4 (Web Text))

Max Activating Token Index: 156

Text #2

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0292. Min Act: -0.0002

Data Index: 238733 (C4 (Web Text))

Max Activating Token Index: 664

Text #3

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0295. Min Act: -0.0002

Data Index: 975567 (C4 (Web Text))

Max Activating Token Index: 132

Text #4

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0286. Min Act: -0.0002

Data Index: 222477 (C4 (Web Text))

Max Activating Token Index: 656

Text #5

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0282. Min Act: -0.0002

Data Index: 340871 (C4 (Web Text))

Max Activating Token Index: 352

Text #6

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0280. Min Act: -0.0002

Data Index: 964853 (C4 (Web Text))

Max Activating Token Index: 146

Text #7

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0280. Min Act: -0.0002

Data Index: 219835 (C4 (Web Text))

Max Activating Token Index: 639

Text #8

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0278. Min Act: -0.0002

Data Index: 1254125 (C4 (Web Text))

Max Activating Token Index: 35

Text #9

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0273. Min Act: -0.0002

Data Index: 670309 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0276. Min Act: -0.0002

Data Index: 1132373 (C4 (Web Text))

Max Activating Token Index: 209

Text #11

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0274. Min Act: -0.0002

Data Index: 853833 (C4 (Web Text))

Max Activating Token Index: 120

Text #12

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1463144 (Python Code)

Max Activating Token Index: 188

Text #13

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0268. Min Act: -0.0002

Data Index: 359826 (C4 (Web Text))

Max Activating Token Index: 2

Text #14

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0268. Min Act: -0.0002

Data Index: 435821 (C4 (Web Text))

Max Activating Token Index: 2

Text #15

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0267. Min Act: -0.0002

Data Index: 305290 (C4 (Web Text))

Max Activating Token Index: 885

Text #16

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1258192 (C4 (Web Text))

Max Activating Token Index: 585

Text #17

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1011443 (C4 (Web Text))

Max Activating Token Index: 10

Text #18

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0272. Min Act: -0.0002

Data Index: 407302 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 0.0306. Min Range: -0.0306

Max Act: 0.0269. Min Act: -0.0002

Data Index: 95906 (C4 (Web Text))

Max Activating Token Index: 4