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

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

Neuron 3771 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0325. Min Act: -0.0003

Data Index: 713510 (C4 (Web Text))

Max Activating Token Index: 66

Text #1

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0310. Min Act: -0.0003

Data Index: 1345911 (C4 (Web Text))

Max Activating Token Index: 56

Text #2

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0293. Min Act: -0.0003

Data Index: 617936 (C4 (Web Text))

Max Activating Token Index: 435

Text #3

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0288. Min Act: -0.0003

Data Index: 1160418 (C4 (Web Text))

Max Activating Token Index: 65

Text #4

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1479027 (Python Code)

Max Activating Token Index: 484

Text #5

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0275. Min Act: -0.0002

Data Index: 1103073 (C4 (Web Text))

Max Activating Token Index: 124

Text #6

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0272. Min Act: -0.0003

Data Index: 1375586 (Python Code)

Max Activating Token Index: 423

Text #7

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1575197 (Python Code)

Max Activating Token Index: 187

Text #8

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0257. Min Act: -0.0003

Data Index: 958044 (C4 (Web Text))

Max Activating Token Index: 694

Text #9

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0265. Min Act: -0.0002

Data Index: 1366856 (Python Code)

Max Activating Token Index: 966

Text #10

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0256. Min Act: -0.0003

Data Index: 166306 (C4 (Web Text))

Max Activating Token Index: 239

Text #11

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0256. Min Act: -0.0003

Data Index: 958655 (C4 (Web Text))

Max Activating Token Index: 783

Text #12

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0258. Min Act: -0.0003

Data Index: 590626 (C4 (Web Text))

Max Activating Token Index: 61

Text #13

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0256. Min Act: -0.0003

Data Index: 1319120 (C4 (Web Text))

Max Activating Token Index: 415

Text #14

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0264. Min Act: -0.0002

Data Index: 584792 (C4 (Web Text))

Max Activating Token Index: 579

Text #15

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0248. Min Act: -0.0002

Data Index: 910364 (C4 (Web Text))

Max Activating Token Index: 323

Text #16

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0247. Min Act: -0.0003

Data Index: 697152 (C4 (Web Text))

Max Activating Token Index: 93

Text #17

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0237. Min Act: -0.0003

Data Index: 1238500 (C4 (Web Text))

Max Activating Token Index: 226

Text #18

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0236. Min Act: -0.0003

Data Index: 365927 (C4 (Web Text))

Max Activating Token Index: 682

Text #19

Max Range: 0.0325. Min Range: -0.0325

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1535807 (Python Code)

Max Activating Token Index: 522