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

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

Neuron 1900 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: 0.0357. Min Range: -0.0357

Max Act: 0.0357. Min Act: -0.0002

Data Index: 962562 (C4 (Web Text))

Max Activating Token Index: 254

Text #1

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0354. Min Act: -0.0002

Data Index: 262178 (C4 (Web Text))

Max Activating Token Index: 221

Text #2

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0281. Min Act: -0.0002

Data Index: 98537 (C4 (Web Text))

Max Activating Token Index: 326

Text #3

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0284. Min Act: -0.0002

Data Index: 628524 (C4 (Web Text))

Max Activating Token Index: 246

Text #4

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0318. Min Act: -0.0002

Data Index: 187334 (C4 (Web Text))

Max Activating Token Index: 516

Text #5

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1003343 (C4 (Web Text))

Max Activating Token Index: 69

Text #6

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0307. Min Act: -0.0002

Data Index: 231860 (C4 (Web Text))

Max Activating Token Index: 972

Text #7

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0300. Min Act: -0.0002

Data Index: 62548 (C4 (Web Text))

Max Activating Token Index: 30

Text #8

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1179677 (C4 (Web Text))

Max Activating Token Index: 171

Text #9

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0314. Min Act: -0.0002

Data Index: 330027 (C4 (Web Text))

Max Activating Token Index: 192

Text #10

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0285. Min Act: -0.0002

Data Index: 329752 (C4 (Web Text))

Max Activating Token Index: 6

Text #11

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0284. Min Act: -0.0002

Data Index: 796566 (C4 (Web Text))

Max Activating Token Index: 548

Text #12

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0291. Min Act: -0.0002

Data Index: 1032957 (C4 (Web Text))

Max Activating Token Index: 183

Text #13

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0278. Min Act: -0.0002

Data Index: 635077 (C4 (Web Text))

Max Activating Token Index: 598

Text #14

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0296. Min Act: -0.0002

Data Index: 585723 (C4 (Web Text))

Max Activating Token Index: 1011

Text #15

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0290. Min Act: -0.0002

Data Index: 1150653 (C4 (Web Text))

Max Activating Token Index: 659

Text #16

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0262. Min Act: -0.0002

Data Index: 507016 (C4 (Web Text))

Max Activating Token Index: 591

Text #17

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1188259 (C4 (Web Text))

Max Activating Token Index: 592

Text #18

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0265. Min Act: -0.0002

Data Index: 798746 (C4 (Web Text))

Max Activating Token Index: 558

Text #19

Max Range: 0.0357. Min Range: -0.0357

Max Act: 0.0316. Min Act: -0.0002

Data Index: 790527 (C4 (Web Text))

Max Activating Token Index: 377