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

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

Neuron 4528 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: 0.0369. Min Range: -0.0369

Max Act: 0.0369. Min Act: -0.0002

Data Index: 621301 (C4 (Web Text))

Max Activating Token Index: 10

Text #1

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0360. Min Act: -0.0001

Data Index: 1233627 (C4 (Web Text))

Max Activating Token Index: 26

Text #2

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0321. Min Act: -0.0002

Data Index: 205483 (C4 (Web Text))

Max Activating Token Index: 23

Text #3

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0313. Min Act: -0.0002

Data Index: 993263 (C4 (Web Text))

Max Activating Token Index: 58

Text #4

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0309. Min Act: -0.0002

Data Index: 340987 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0309. Min Act: -0.0002

Data Index: 912357 (C4 (Web Text))

Max Activating Token Index: 17

Text #6

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0308. Min Act: -0.0001

Data Index: 1135102 (C4 (Web Text))

Max Activating Token Index: 929

Text #7

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0306. Min Act: -0.0002

Data Index: 883659 (C4 (Web Text))

Max Activating Token Index: 443

Text #8

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0300. Min Act: -0.0002

Data Index: 596491 (C4 (Web Text))

Max Activating Token Index: 25

Text #9

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0286. Min Act: -0.0002

Data Index: 529719 (C4 (Web Text))

Max Activating Token Index: 23

Text #10

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0285. Min Act: -0.0002

Data Index: 399655 (C4 (Web Text))

Max Activating Token Index: 994

Text #11

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1020838 (C4 (Web Text))

Max Activating Token Index: 9

Text #12

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0272. Min Act: -0.0002

Data Index: 268803 (C4 (Web Text))

Max Activating Token Index: 9

Text #13

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0272. Min Act: -0.0002

Data Index: 187820 (C4 (Web Text))

Max Activating Token Index: 14

Text #14

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0265. Min Act: -0.0002

Data Index: 560285 (C4 (Web Text))

Max Activating Token Index: 37

Text #15

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0268. Min Act: -0.0002

Data Index: 624148 (C4 (Web Text))

Max Activating Token Index: 60

Text #16

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0267. Min Act: -0.0002

Data Index: 313236 (C4 (Web Text))

Max Activating Token Index: 559

Text #17

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1184344 (C4 (Web Text))

Max Activating Token Index: 13

Text #18

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0263. Min Act: -0.0002

Data Index: 877831 (C4 (Web Text))

Max Activating Token Index: 62

Text #19

Max Range: 0.0369. Min Range: -0.0369

Max Act: 0.0257. Min Act: -0.0002

Data Index: 271370 (C4 (Web Text))

Max Activating Token Index: 29