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

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

Neuron 2522 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: 0.0448. Min Range: -0.0448

Max Act: 0.0448. Min Act: -0.0003

Data Index: 625537 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0418. Min Act: -0.0002

Data Index: 167949 (C4 (Web Text))

Max Activating Token Index: 213

Text #2

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0399. Min Act: -0.0002

Data Index: 378267 (C4 (Web Text))

Max Activating Token Index: 383

Text #3

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0359. Min Act: -0.0002

Data Index: 1254886 (C4 (Web Text))

Max Activating Token Index: 573

Text #4

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0356. Min Act: -0.0003

Data Index: 1260390 (C4 (Web Text))

Max Activating Token Index: 202

Text #5

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0315. Min Act: -0.0003

Data Index: 1079547 (C4 (Web Text))

Max Activating Token Index: 801

Text #6

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0317. Min Act: -0.0002

Data Index: 756834 (C4 (Web Text))

Max Activating Token Index: 122

Text #7

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0307. Min Act: -0.0003

Data Index: 742374 (C4 (Web Text))

Max Activating Token Index: 407

Text #8

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0296. Min Act: -0.0003

Data Index: 507865 (C4 (Web Text))

Max Activating Token Index: 667

Text #9

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0284. Min Act: -0.0003

Data Index: 447620 (C4 (Web Text))

Max Activating Token Index: 755

Text #10

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0288. Min Act: -0.0002

Data Index: 715216 (C4 (Web Text))

Max Activating Token Index: 968

Text #11

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0278. Min Act: -0.0003

Data Index: 212659 (C4 (Web Text))

Max Activating Token Index: 577

Text #12

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0264. Min Act: -0.0002

Data Index: 1011772 (C4 (Web Text))

Max Activating Token Index: 203

Text #13

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0263. Min Act: -0.0002

Data Index: 358777 (C4 (Web Text))

Max Activating Token Index: 260

Text #14

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0268. Min Act: -0.0002

Data Index: 33233 (C4 (Web Text))

Max Activating Token Index: 318

Text #15

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0255. Min Act: -0.0003

Data Index: 918340 (C4 (Web Text))

Max Activating Token Index: 854

Text #16

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0241. Min Act: -0.0003

Data Index: 678508 (C4 (Web Text))

Max Activating Token Index: 510

Text #17

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0238. Min Act: -0.0003

Data Index: 663546 (C4 (Web Text))

Max Activating Token Index: 972

Text #18

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1291114 (C4 (Web Text))

Max Activating Token Index: 205

Text #19

Max Range: 0.0448. Min Range: -0.0448

Max Act: 0.0228. Min Act: -0.0003

Data Index: 1181511 (C4 (Web Text))

Max Activating Token Index: 627