Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 4733 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0477. Min Act: -0.0002

Data Index: 834093 (C4 (Web Text))

Max Activating Token Index: 545

Text #1

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0391. Min Act: -0.0002

Data Index: 257414 (C4 (Web Text))

Max Activating Token Index: 488

Text #2

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0380. Min Act: -0.0002

Data Index: 1311052 (C4 (Web Text))

Max Activating Token Index: 71

Text #3

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0377. Min Act: -0.0002

Data Index: 120116 (C4 (Web Text))

Max Activating Token Index: 512

Text #4

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0350. Min Act: -0.0002

Data Index: 88650 (C4 (Web Text))

Max Activating Token Index: 169

Text #5

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0350. Min Act: -0.0002

Data Index: 1338804 (C4 (Web Text))

Max Activating Token Index: 721

Text #6

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0348. Min Act: -0.0002

Data Index: 1036512 (C4 (Web Text))

Max Activating Token Index: 111

Text #7

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0314. Min Act: -0.0002

Data Index: 209956 (C4 (Web Text))

Max Activating Token Index: 319

Text #8

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0304. Min Act: -0.0002

Data Index: 312864 (C4 (Web Text))

Max Activating Token Index: 340

Text #9

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0299. Min Act: -0.0002

Data Index: 789055 (C4 (Web Text))

Max Activating Token Index: 171

Text #10

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0286. Min Act: -0.0002

Data Index: 324352 (C4 (Web Text))

Max Activating Token Index: 727

Text #11

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0286. Min Act: -0.0002

Data Index: 1046344 (C4 (Web Text))

Max Activating Token Index: 770

Text #12

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0274. Min Act: -0.0002

Data Index: 1077692 (C4 (Web Text))

Max Activating Token Index: 340

Text #13

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0289. Min Act: -0.0002

Data Index: 1286563 (C4 (Web Text))

Max Activating Token Index: 710

Text #14

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0275. Min Act: -0.0002

Data Index: 384234 (C4 (Web Text))

Max Activating Token Index: 38

Text #15

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0256. Min Act: -0.0002

Data Index: 1197901 (C4 (Web Text))

Max Activating Token Index: 298

Text #16

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0279. Min Act: -0.0002

Data Index: 1056814 (C4 (Web Text))

Max Activating Token Index: 666

Text #17

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0272. Min Act: -0.0002

Data Index: 1197736 (C4 (Web Text))

Max Activating Token Index: 111

Text #18

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0269. Min Act: -0.0002

Data Index: 387333 (C4 (Web Text))

Max Activating Token Index: 321

Text #19

Max Range: 0.0477. Min Range: -0.0477

Max Act: 0.0270. Min Act: -0.0002

Data Index: 230989 (C4 (Web Text))

Max Activating Token Index: 657