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

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

Neuron 3119 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: 0.0390. Min Range: -0.0390

Max Act: 0.0390. Min Act: -0.0003

Data Index: 922453 (C4 (Web Text))

Max Activating Token Index: 83

Text #1

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0370. Min Act: -0.0003

Data Index: 872501 (C4 (Web Text))

Max Activating Token Index: 620

Text #2

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0364. Min Act: -0.0002

Data Index: 534268 (C4 (Web Text))

Max Activating Token Index: 9

Text #3

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0363. Min Act: -0.0003

Data Index: 616041 (C4 (Web Text))

Max Activating Token Index: 34

Text #4

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0356. Min Act: -0.0002

Data Index: 636763 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0353. Min Act: -0.0003

Data Index: 62781 (C4 (Web Text))

Max Activating Token Index: 9

Text #6

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0354. Min Act: -0.0003

Data Index: 677115 (C4 (Web Text))

Max Activating Token Index: 92

Text #7

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0343. Min Act: -0.0003

Data Index: 1248129 (C4 (Web Text))

Max Activating Token Index: 928

Text #8

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0329. Min Act: -0.0003

Data Index: 264852 (C4 (Web Text))

Max Activating Token Index: 761

Text #9

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0334. Min Act: -0.0003

Data Index: 234885 (C4 (Web Text))

Max Activating Token Index: 833

Text #10

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0315. Min Act: -0.0003

Data Index: 900230 (C4 (Web Text))

Max Activating Token Index: 916

Text #11

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0321. Min Act: -0.0002

Data Index: 1136465 (C4 (Web Text))

Max Activating Token Index: 747

Text #12

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0321. Min Act: -0.0002

Data Index: 98578 (C4 (Web Text))

Max Activating Token Index: 423

Text #13

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0318. Min Act: -0.0003

Data Index: 41824 (C4 (Web Text))

Max Activating Token Index: 779

Text #14

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0317. Min Act: -0.0003

Data Index: 797048 (C4 (Web Text))

Max Activating Token Index: 337

Text #15

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0327. Min Act: -0.0003

Data Index: 478099 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0308. Min Act: -0.0003

Data Index: 1111022 (C4 (Web Text))

Max Activating Token Index: 213

Text #17

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0313. Min Act: -0.0003

Data Index: 837661 (C4 (Web Text))

Max Activating Token Index: 771

Text #18

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0318. Min Act: -0.0002

Data Index: 1026617 (C4 (Web Text))

Max Activating Token Index: 133

Text #19

Max Range: 0.0390. Min Range: -0.0390

Max Act: 0.0323. Min Act: -0.0003

Data Index: 171863 (C4 (Web Text))

Max Activating Token Index: 671