Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 778 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0299. Min Act: -0.0003

Data Index: 1243796 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0273. Min Act: -0.0004

Data Index: 720355 (C4 (Web Text))

Max Activating Token Index: 932

Text #2

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0275. Min Act: -0.0004

Data Index: 126413 (C4 (Web Text))

Max Activating Token Index: 564

Text #3

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0255. Min Act: -0.0003

Data Index: 189518 (C4 (Web Text))

Max Activating Token Index: 1014

Text #4

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0265. Min Act: -0.0003

Data Index: 1055151 (C4 (Web Text))

Max Activating Token Index: 580

Text #5

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0267. Min Act: -0.0003

Data Index: 726387 (C4 (Web Text))

Max Activating Token Index: 694

Text #6

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0274. Min Act: -0.0003

Data Index: 1265621 (C4 (Web Text))

Max Activating Token Index: 855

Text #7

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0258. Min Act: -0.0003

Data Index: 1270594 (C4 (Web Text))

Max Activating Token Index: 765

Text #8

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0265. Min Act: -0.0003

Data Index: 499886 (C4 (Web Text))

Max Activating Token Index: 653

Text #9

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0256. Min Act: -0.0002

Data Index: 525955 (C4 (Web Text))

Max Activating Token Index: 969

Text #10

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0251. Min Act: -0.0004

Data Index: 1019992 (C4 (Web Text))

Max Activating Token Index: 913

Text #11

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0238. Min Act: -0.0003

Data Index: 170353 (C4 (Web Text))

Max Activating Token Index: 628

Text #12

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0262. Min Act: -0.0003

Data Index: 1087710 (C4 (Web Text))

Max Activating Token Index: 216

Text #13

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0241. Min Act: -0.0003

Data Index: 1311780 (C4 (Web Text))

Max Activating Token Index: 784

Text #14

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0249. Min Act: -0.0003

Data Index: 509001 (C4 (Web Text))

Max Activating Token Index: 739

Text #15

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0246. Min Act: -0.0002

Data Index: 1027209 (C4 (Web Text))

Max Activating Token Index: 456

Text #16

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0246. Min Act: -0.0003

Data Index: 862288 (C4 (Web Text))

Max Activating Token Index: 371

Text #17

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0242. Min Act: -0.0003

Data Index: 345999 (C4 (Web Text))

Max Activating Token Index: 698

Text #18

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0253. Min Act: -0.0003

Data Index: 342468 (C4 (Web Text))

Max Activating Token Index: 464

Text #19

Max Range: 0.0299. Min Range: -0.0299

Max Act: 0.0239. Min Act: -0.0004

Data Index: 510414 (C4 (Web Text))

Max Activating Token Index: 673