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

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

Neuron 4772 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: 0.0367. Min Range: -0.0367

Max Act: 0.0367. Min Act: -0.0003

Data Index: 521874 (C4 (Web Text))

Max Activating Token Index: 395

Text #1

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0345. Min Act: -0.0003

Data Index: 98162 (C4 (Web Text))

Max Activating Token Index: 706

Text #2

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0342. Min Act: -0.0002

Data Index: 948567 (C4 (Web Text))

Max Activating Token Index: 211

Text #3

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0337. Min Act: -0.0003

Data Index: 215635 (C4 (Web Text))

Max Activating Token Index: 764

Text #4

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0325. Min Act: -0.0002

Data Index: 1193207 (C4 (Web Text))

Max Activating Token Index: 42

Text #5

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0322. Min Act: -0.0002

Data Index: 551321 (C4 (Web Text))

Max Activating Token Index: 41

Text #6

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0313. Min Act: -0.0002

Data Index: 1289703 (C4 (Web Text))

Max Activating Token Index: 88

Text #7

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0296. Min Act: -0.0002

Data Index: 888918 (C4 (Web Text))

Max Activating Token Index: 231

Text #8

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0305. Min Act: -0.0003

Data Index: 983455 (C4 (Web Text))

Max Activating Token Index: 767

Text #9

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0288. Min Act: -0.0003

Data Index: 116625 (C4 (Web Text))

Max Activating Token Index: 686

Text #10

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0296. Min Act: -0.0003

Data Index: 571506 (C4 (Web Text))

Max Activating Token Index: 354

Text #11

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1100070 (C4 (Web Text))

Max Activating Token Index: 368

Text #12

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0293. Min Act: -0.0002

Data Index: 792586 (C4 (Web Text))

Max Activating Token Index: 260

Text #13

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0290. Min Act: -0.0003

Data Index: 848315 (C4 (Web Text))

Max Activating Token Index: 138

Text #14

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0279. Min Act: -0.0003

Data Index: 1294231 (C4 (Web Text))

Max Activating Token Index: 183

Text #15

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0271. Min Act: -0.0003

Data Index: 557376 (C4 (Web Text))

Max Activating Token Index: 244

Text #16

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0280. Min Act: -0.0002

Data Index: 1006934 (C4 (Web Text))

Max Activating Token Index: 687

Text #17

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0273. Min Act: -0.0002

Data Index: 1198314 (C4 (Web Text))

Max Activating Token Index: 107

Text #18

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0274. Min Act: -0.0003

Data Index: 673309 (C4 (Web Text))

Max Activating Token Index: 170

Text #19

Max Range: 0.0367. Min Range: -0.0367

Max Act: 0.0272. Min Act: -0.0003

Data Index: 264309 (C4 (Web Text))

Max Activating Token Index: 42