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

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

Neuron 391 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: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0002

Data Index: 1456713 (Python Code)

Max Activating Token Index: 463

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0251. Min Act: -0.0002

Data Index: 447371 (C4 (Web Text))

Max Activating Token Index: 902

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0241. Min Act: -0.0002

Data Index: 1647353 (Python Code)

Max Activating Token Index: 453

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0230. Min Act: -0.0003

Data Index: 1366517 (Python Code)

Max Activating Token Index: 517

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0216. Min Act: -0.0003

Data Index: 1197873 (C4 (Web Text))

Max Activating Token Index: 862

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0220. Min Act: -0.0003

Data Index: 363974 (C4 (Web Text))

Max Activating Token Index: 506

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0222. Min Act: -0.0002

Data Index: 1622617 (Python Code)

Max Activating Token Index: 735

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0218. Min Act: -0.0003

Data Index: 1360261 (Python Code)

Max Activating Token Index: 684

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0208. Min Act: -0.0003

Data Index: 1404832 (Python Code)

Max Activating Token Index: 1023

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0217. Min Act: -0.0002

Data Index: 1108993 (C4 (Web Text))

Max Activating Token Index: 395

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0198. Min Act: -0.0003

Data Index: 1533796 (Python Code)

Max Activating Token Index: 320

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0220. Min Act: -0.0003

Data Index: 992740 (C4 (Web Text))

Max Activating Token Index: 755

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0214. Min Act: -0.0003

Data Index: 601685 (C4 (Web Text))

Max Activating Token Index: 914

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0204. Min Act: -0.0003

Data Index: 194320 (C4 (Web Text))

Max Activating Token Index: 167

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0209. Min Act: -0.0003

Data Index: 1178295 (C4 (Web Text))

Max Activating Token Index: 667

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1434947 (Python Code)

Max Activating Token Index: 837

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0200. Min Act: -0.0003

Data Index: 571702 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0197. Min Act: -0.0003

Data Index: 1164747 (C4 (Web Text))

Max Activating Token Index: 692

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0204. Min Act: -0.0003

Data Index: 1178955 (C4 (Web Text))

Max Activating Token Index: 675

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0195. Min Act: -0.0003

Data Index: 234721 (C4 (Web Text))

Max Activating Token Index: 7