Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 119 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0421. Min Act: -0.0005

Data Index: 57327 (C4 (Web Text))

Max Activating Token Index: 59

Text #1

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0350. Min Act: -0.0005

Data Index: 834934 (C4 (Web Text))

Max Activating Token Index: 801

Text #2

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0323. Min Act: -0.0005

Data Index: 997623 (C4 (Web Text))

Max Activating Token Index: 787

Text #3

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0313. Min Act: -0.0005

Data Index: 221854 (C4 (Web Text))

Max Activating Token Index: 88

Text #4

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0329. Min Act: -0.0005

Data Index: 894287 (C4 (Web Text))

Max Activating Token Index: 683

Text #5

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0307. Min Act: -0.0005

Data Index: 339298 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0321. Min Act: -0.0005

Data Index: 566694 (C4 (Web Text))

Max Activating Token Index: 355

Text #7

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0319. Min Act: -0.0005

Data Index: 771931 (C4 (Web Text))

Max Activating Token Index: 272

Text #8

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0314. Min Act: -0.0005

Data Index: 808168 (C4 (Web Text))

Max Activating Token Index: 406

Text #9

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0286. Min Act: -0.0005

Data Index: 1229198 (C4 (Web Text))

Max Activating Token Index: 743

Text #10

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0285. Min Act: -0.0005

Data Index: 1039576 (C4 (Web Text))

Max Activating Token Index: 454

Text #11

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0282. Min Act: -0.0005

Data Index: 667277 (C4 (Web Text))

Max Activating Token Index: 675

Text #12

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0295. Min Act: -0.0005

Data Index: 383517 (C4 (Web Text))

Max Activating Token Index: 572

Text #13

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0293. Min Act: -0.0005

Data Index: 979601 (C4 (Web Text))

Max Activating Token Index: 862

Text #14

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0301. Min Act: -0.0005

Data Index: 770475 (C4 (Web Text))

Max Activating Token Index: 733

Text #15

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0287. Min Act: -0.0005

Data Index: 594661 (C4 (Web Text))

Max Activating Token Index: 278

Text #16

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0274. Min Act: -0.0005

Data Index: 1243418 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0287. Min Act: -0.0005

Data Index: 1062784 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0281. Min Act: -0.0005

Data Index: 958965 (C4 (Web Text))

Max Activating Token Index: 199

Text #19

Max Range: 0.0421. Min Range: -0.0421

Max Act: 0.0310. Min Act: -0.0005

Data Index: 338072 (C4 (Web Text))

Max Activating Token Index: 668