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

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

Neuron 4326 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: 0.0579. Min Range: -0.0579

Max Act: 0.0579. Min Act: -0.0002

Data Index: 783785 (C4 (Web Text))

Max Activating Token Index: 303

Text #1

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0498. Min Act: -0.0002

Data Index: 1277654 (C4 (Web Text))

Max Activating Token Index: 925

Text #2

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0485. Min Act: -0.0002

Data Index: 753996 (C4 (Web Text))

Max Activating Token Index: 537

Text #3

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0472. Min Act: -0.0002

Data Index: 529196 (C4 (Web Text))

Max Activating Token Index: 177

Text #4

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0351. Min Act: -0.0003

Data Index: 1227993 (C4 (Web Text))

Max Activating Token Index: 463

Text #5

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0312. Min Act: -0.0003

Data Index: 348422 (C4 (Web Text))

Max Activating Token Index: 70

Text #6

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0310. Min Act: -0.0003

Data Index: 326451 (C4 (Web Text))

Max Activating Token Index: 168

Text #7

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0299. Min Act: -0.0003

Data Index: 700051 (C4 (Web Text))

Max Activating Token Index: 353

Text #8

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0287. Min Act: -0.0003

Data Index: 592638 (C4 (Web Text))

Max Activating Token Index: 52

Text #9

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0285. Min Act: -0.0003

Data Index: 221587 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0295. Min Act: -0.0003

Data Index: 1258307 (C4 (Web Text))

Max Activating Token Index: 744

Text #11

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0282. Min Act: -0.0003

Data Index: 918820 (C4 (Web Text))

Max Activating Token Index: 362

Text #12

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0267. Min Act: -0.0003

Data Index: 511965 (C4 (Web Text))

Max Activating Token Index: 581

Text #13

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0277. Min Act: -0.0003

Data Index: 1283755 (C4 (Web Text))

Max Activating Token Index: 707

Text #14

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0275. Min Act: -0.0003

Data Index: 700091 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0270. Min Act: -0.0002

Data Index: 737366 (C4 (Web Text))

Max Activating Token Index: 254

Text #16

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0275. Min Act: -0.0003

Data Index: 880490 (C4 (Web Text))

Max Activating Token Index: 513

Text #17

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0268. Min Act: -0.0003

Data Index: 1033110 (C4 (Web Text))

Max Activating Token Index: 291

Text #18

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0273. Min Act: -0.0003

Data Index: 835869 (C4 (Web Text))

Max Activating Token Index: 478

Text #19

Max Range: 0.0579. Min Range: -0.0579

Max Act: 0.0260. Min Act: -0.0003

Data Index: 677240 (C4 (Web Text))

Max Activating Token Index: 24