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

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

Neuron 1230 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: 0.0343. Min Range: -0.0343

Max Act: 0.0343. Min Act: -0.0006

Data Index: 363268 (C4 (Web Text))

Max Activating Token Index: 887

Text #1

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0324. Min Act: -0.0006

Data Index: 125392 (C4 (Web Text))

Max Activating Token Index: 155

Text #2

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0327. Min Act: -0.0006

Data Index: 577531 (C4 (Web Text))

Max Activating Token Index: 283

Text #3

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0324. Min Act: -0.0006

Data Index: 1198494 (C4 (Web Text))

Max Activating Token Index: 356

Text #4

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0317. Min Act: -0.0006

Data Index: 995668 (C4 (Web Text))

Max Activating Token Index: 605

Text #5

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0305. Min Act: -0.0006

Data Index: 972094 (C4 (Web Text))

Max Activating Token Index: 985

Text #6

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0310. Min Act: -0.0006

Data Index: 944462 (C4 (Web Text))

Max Activating Token Index: 878

Text #7

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0297. Min Act: -0.0006

Data Index: 247777 (C4 (Web Text))

Max Activating Token Index: 461

Text #8

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0303. Min Act: -0.0006

Data Index: 212792 (C4 (Web Text))

Max Activating Token Index: 22

Text #9

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0292. Min Act: -0.0006

Data Index: 89170 (C4 (Web Text))

Max Activating Token Index: 876

Text #10

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0302. Min Act: -0.0006

Data Index: 43741 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0295. Min Act: -0.0006

Data Index: 713731 (C4 (Web Text))

Max Activating Token Index: 467

Text #12

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0282. Min Act: -0.0006

Data Index: 871002 (C4 (Web Text))

Max Activating Token Index: 887

Text #13

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0292. Min Act: -0.0006

Data Index: 357534 (C4 (Web Text))

Max Activating Token Index: 456

Text #14

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0286. Min Act: -0.0006

Data Index: 1242232 (C4 (Web Text))

Max Activating Token Index: 626

Text #15

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0284. Min Act: -0.0006

Data Index: 929342 (C4 (Web Text))

Max Activating Token Index: 56

Text #16

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0277. Min Act: -0.0006

Data Index: 154695 (C4 (Web Text))

Max Activating Token Index: 933

Text #17

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0287. Min Act: -0.0006

Data Index: 1110267 (C4 (Web Text))

Max Activating Token Index: 390

Text #18

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0288. Min Act: -0.0006

Data Index: 1033022 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0343. Min Range: -0.0343

Max Act: 0.0292. Min Act: -0.0006

Data Index: 99775 (C4 (Web Text))

Max Activating Token Index: 48