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

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

Neuron 787 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0329. Min Act: -0.0006

Data Index: 867519 (C4 (Web Text))

Max Activating Token Index: 496

Text #1

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0315. Min Act: -0.0006

Data Index: 967024 (C4 (Web Text))

Max Activating Token Index: 429

Text #2

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0294. Min Act: -0.0006

Data Index: 294426 (C4 (Web Text))

Max Activating Token Index: 815

Text #3

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0284. Min Act: -0.0006

Data Index: 640982 (C4 (Web Text))

Max Activating Token Index: 301

Text #4

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0283. Min Act: -0.0005

Data Index: 655612 (C4 (Web Text))

Max Activating Token Index: 539

Text #5

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0264. Min Act: -0.0006

Data Index: 99817 (C4 (Web Text))

Max Activating Token Index: 555

Text #6

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0257. Min Act: -0.0006

Data Index: 177452 (C4 (Web Text))

Max Activating Token Index: 633

Text #7

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0263. Min Act: -0.0006

Data Index: 975879 (C4 (Web Text))

Max Activating Token Index: 875

Text #8

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0257. Min Act: -0.0006

Data Index: 908666 (C4 (Web Text))

Max Activating Token Index: 826

Text #9

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0268. Min Act: -0.0006

Data Index: 1165745 (C4 (Web Text))

Max Activating Token Index: 238

Text #10

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0264. Min Act: -0.0006

Data Index: 884305 (C4 (Web Text))

Max Activating Token Index: 198

Text #11

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0258. Min Act: -0.0006

Data Index: 621515 (C4 (Web Text))

Max Activating Token Index: 481

Text #12

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0239. Min Act: -0.0006

Data Index: 666290 (C4 (Web Text))

Max Activating Token Index: 845

Text #13

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0255. Min Act: -0.0006

Data Index: 844746 (C4 (Web Text))

Max Activating Token Index: 825

Text #14

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0260. Min Act: -0.0006

Data Index: 1064427 (C4 (Web Text))

Max Activating Token Index: 786

Text #15

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0248. Min Act: -0.0006

Data Index: 852618 (C4 (Web Text))

Max Activating Token Index: 23

Text #16

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0248. Min Act: -0.0006

Data Index: 1251070 (C4 (Web Text))

Max Activating Token Index: 161

Text #17

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0252. Min Act: -0.0006

Data Index: 847157 (C4 (Web Text))

Max Activating Token Index: 782

Text #18

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0252. Min Act: -0.0006

Data Index: 959682 (C4 (Web Text))

Max Activating Token Index: 272

Text #19

Max Range: 0.0329. Min Range: -0.0329

Max Act: 0.0240. Min Act: -0.0006

Data Index: 811460 (C4 (Web Text))

Max Activating Token Index: 555