Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1000 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0337. Min Act: -0.0004

Data Index: 1257357 (C4 (Web Text))

Max Activating Token Index: 582

Text #1

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0332. Min Act: -0.0001

Data Index: 814416 (C4 (Web Text))

Max Activating Token Index: 219

Text #2

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0325. Min Act: -0.0003

Data Index: 238134 (C4 (Web Text))

Max Activating Token Index: 994

Text #3

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0317. Min Act: -0.0002

Data Index: 7905 (C4 (Web Text))

Max Activating Token Index: 695

Text #4

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0323. Min Act: -0.0000

Data Index: 773244 (C4 (Web Text))

Max Activating Token Index: 85

Text #5

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0318. Min Act: -0.0003

Data Index: 124367 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0320. Min Act: -0.0003

Data Index: 104976 (C4 (Web Text))

Max Activating Token Index: 288

Text #7

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0312. Min Act: -0.0003

Data Index: 551452 (C4 (Web Text))

Max Activating Token Index: 523

Text #8

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0312. Min Act: -0.0002

Data Index: 1342948 (C4 (Web Text))

Max Activating Token Index: 212

Text #9

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0313. Min Act: -0.0003

Data Index: 858507 (C4 (Web Text))

Max Activating Token Index: 468

Text #10

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0308. Min Act: -0.0003

Data Index: 687824 (C4 (Web Text))

Max Activating Token Index: 583

Text #11

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0311. Min Act: -0.0003

Data Index: 165355 (C4 (Web Text))

Max Activating Token Index: 111

Text #12

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0299. Min Act: -0.0003

Data Index: 316616 (C4 (Web Text))

Max Activating Token Index: 580

Text #13

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0298. Min Act: -0.0004

Data Index: 280385 (C4 (Web Text))

Max Activating Token Index: 207

Text #14

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0296. Min Act: -0.0003

Data Index: 588588 (C4 (Web Text))

Max Activating Token Index: 811

Text #15

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0302. Min Act: -0.0003

Data Index: 109579 (C4 (Web Text))

Max Activating Token Index: 700

Text #16

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0295. Min Act: -0.0003

Data Index: 188984 (C4 (Web Text))

Max Activating Token Index: 408

Text #17

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0296. Min Act: -0.0003

Data Index: 261653 (C4 (Web Text))

Max Activating Token Index: 318

Text #18

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0297. Min Act: -0.0003

Data Index: 679370 (C4 (Web Text))

Max Activating Token Index: 934

Text #19

Max Range: 0.0337. Min Range: -0.0337

Max Act: 0.0292. Min Act: -0.0003

Data Index: 1303794 (C4 (Web Text))

Max Activating Token Index: 715