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

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

Neuron 3653 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0375. Min Act: -0.0002

Data Index: 1554703 (Python Code)

Max Activating Token Index: 804

Text #1

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0341. Min Act: -0.0002

Data Index: 936132 (C4 (Web Text))

Max Activating Token Index: 4

Text #2

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0328. Min Act: -0.0002

Data Index: 394204 (C4 (Web Text))

Max Activating Token Index: 2

Text #3

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0328. Min Act: -0.0002

Data Index: 456648 (C4 (Web Text))

Max Activating Token Index: 2

Text #4

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0328. Min Act: -0.0002

Data Index: 193051 (C4 (Web Text))

Max Activating Token Index: 2

Text #5

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0313. Min Act: -0.0002

Data Index: 70086 (C4 (Web Text))

Max Activating Token Index: 550

Text #6

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1227316 (C4 (Web Text))

Max Activating Token Index: 395

Text #7

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0277. Min Act: -0.0002

Data Index: 487055 (C4 (Web Text))

Max Activating Token Index: 7

Text #8

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1303635 (C4 (Web Text))

Max Activating Token Index: 771

Text #9

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0271. Min Act: -0.0002

Data Index: 311083 (C4 (Web Text))

Max Activating Token Index: 4

Text #10

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0272. Min Act: -0.0002

Data Index: 505901 (C4 (Web Text))

Max Activating Token Index: 437

Text #11

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0274. Min Act: -0.0002

Data Index: 945452 (C4 (Web Text))

Max Activating Token Index: 6

Text #12

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0271. Min Act: -0.0002

Data Index: 493301 (C4 (Web Text))

Max Activating Token Index: 767

Text #13

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0258. Min Act: -0.0002

Data Index: 1539260 (Python Code)

Max Activating Token Index: 283

Text #14

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0301. Min Act: -0.0002

Data Index: 163203 (C4 (Web Text))

Max Activating Token Index: 289

Text #15

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0278. Min Act: -0.0002

Data Index: 945253 (C4 (Web Text))

Max Activating Token Index: 661

Text #16

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0284. Min Act: -0.0002

Data Index: 570932 (C4 (Web Text))

Max Activating Token Index: 76

Text #17

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0268. Min Act: -0.0002

Data Index: 505192 (C4 (Web Text))

Max Activating Token Index: 1010

Text #18

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0273. Min Act: -0.0002

Data Index: 937607 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0375. Min Range: -0.0375

Max Act: 0.0279. Min Act: -0.0002

Data Index: 29654 (C4 (Web Text))

Max Activating Token Index: 721