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

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

Neuron 5118 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: 0.0344. Min Range: -0.0344

Max Act: 0.0344. Min Act: -0.0003

Data Index: 768383 (C4 (Web Text))

Max Activating Token Index: 956

Text #1

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0329. Min Act: -0.0003

Data Index: 517656 (C4 (Web Text))

Max Activating Token Index: 915

Text #2

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0321. Min Act: -0.0002

Data Index: 150118 (C4 (Web Text))

Max Activating Token Index: 202

Text #3

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0317. Min Act: -0.0002

Data Index: 1346592 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0315. Min Act: -0.0003

Data Index: 856795 (C4 (Web Text))

Max Activating Token Index: 177

Text #5

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0304. Min Act: -0.0003

Data Index: 1592232 (Python Code)

Max Activating Token Index: 8

Text #6

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0296. Min Act: -0.0003

Data Index: 779972 (C4 (Web Text))

Max Activating Token Index: 879

Text #7

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0289. Min Act: -0.0003

Data Index: 607390 (C4 (Web Text))

Max Activating Token Index: 420

Text #8

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0282. Min Act: -0.0003

Data Index: 398411 (C4 (Web Text))

Max Activating Token Index: 56

Text #9

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0002

Data Index: 700497 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0281. Min Act: -0.0002

Data Index: 1146879 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0267. Min Act: -0.0003

Data Index: 356109 (C4 (Web Text))

Max Activating Token Index: 214

Text #12

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0270. Min Act: -0.0003

Data Index: 467705 (C4 (Web Text))

Max Activating Token Index: 154

Text #13

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0282. Min Act: -0.0003

Data Index: 1162275 (C4 (Web Text))

Max Activating Token Index: 768

Text #14

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0278. Min Act: -0.0003

Data Index: 598107 (C4 (Web Text))

Max Activating Token Index: 589

Text #15

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0282. Min Act: -0.0003

Data Index: 503897 (C4 (Web Text))

Max Activating Token Index: 91

Text #16

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0265. Min Act: -0.0003

Data Index: 140140 (C4 (Web Text))

Max Activating Token Index: 310

Text #17

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0263. Min Act: -0.0002

Data Index: 326980 (C4 (Web Text))

Max Activating Token Index: 724

Text #18

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0291. Min Act: -0.0003

Data Index: 914797 (C4 (Web Text))

Max Activating Token Index: 210

Text #19

Max Range: 0.0344. Min Range: -0.0344

Max Act: 0.0268. Min Act: -0.0003

Data Index: 133498 (C4 (Web Text))

Max Activating Token Index: 844