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

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

Neuron 2124 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0295. Min Act: -0.0002

Data Index: 1259957 (C4 (Web Text))

Max Activating Token Index: 859

Text #1

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0293. Min Act: -0.0002

Data Index: 31382 (C4 (Web Text))

Max Activating Token Index: 444

Text #2

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0282. Min Act: -0.0002

Data Index: 905482 (C4 (Web Text))

Max Activating Token Index: 442

Text #3

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0278. Min Act: -0.0002

Data Index: 248831 (C4 (Web Text))

Max Activating Token Index: 434

Text #4

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0279. Min Act: -0.0002

Data Index: 602773 (C4 (Web Text))

Max Activating Token Index: 783

Text #5

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0265. Min Act: -0.0002

Data Index: 296600 (C4 (Web Text))

Max Activating Token Index: 94

Text #6

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0263. Min Act: -0.0002

Data Index: 1359531 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0262. Min Act: -0.0002

Data Index: 1163533 (C4 (Web Text))

Max Activating Token Index: 14

Text #8

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0260. Min Act: -0.0002

Data Index: 1343822 (C4 (Web Text))

Max Activating Token Index: 730

Text #9

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0255. Min Act: -0.0002

Data Index: 21265 (C4 (Web Text))

Max Activating Token Index: 469

Text #10

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0254. Min Act: -0.0002

Data Index: 1198265 (C4 (Web Text))

Max Activating Token Index: 770

Text #11

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0252. Min Act: -0.0002

Data Index: 570373 (C4 (Web Text))

Max Activating Token Index: 976

Text #12

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0251. Min Act: -0.0002

Data Index: 1642394 (Python Code)

Max Activating Token Index: 20

Text #13

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0251. Min Act: -0.0002

Data Index: 836486 (C4 (Web Text))

Max Activating Token Index: 584

Text #14

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0250. Min Act: -0.0002

Data Index: 609742 (C4 (Web Text))

Max Activating Token Index: 419

Text #15

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0253. Min Act: -0.0002

Data Index: 1042639 (C4 (Web Text))

Max Activating Token Index: 71

Text #16

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0248. Min Act: -0.0002

Data Index: 56972 (C4 (Web Text))

Max Activating Token Index: 208

Text #17

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0252. Min Act: -0.0002

Data Index: 354559 (C4 (Web Text))

Max Activating Token Index: 774

Text #18

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1162209 (C4 (Web Text))

Max Activating Token Index: 410

Text #19

Max Range: 0.0295. Min Range: -0.0295

Max Act: 0.0245. Min Act: -0.0002

Data Index: 1265693 (C4 (Web Text))

Max Activating Token Index: 390