Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 3635 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1466. Min Act: -0.0003

Data Index: 301112 (C4 (Web Text))

Max Activating Token Index: 777

Text #1

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1446. Min Act: -0.0003

Data Index: 198318 (C4 (Web Text))

Max Activating Token Index: 427

Text #2

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1435. Min Act: -0.0003

Data Index: 796386 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1488. Min Act: -0.0003

Data Index: 1112020 (C4 (Web Text))

Max Activating Token Index: 189

Text #4

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1416. Min Act: -0.0003

Data Index: 165715 (C4 (Web Text))

Max Activating Token Index: 607

Text #5

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1354. Min Act: -0.0003

Data Index: 650013 (C4 (Web Text))

Max Activating Token Index: 713

Text #6

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1564. Min Act: -0.0003

Data Index: 390648 (C4 (Web Text))

Max Activating Token Index: 833

Text #7

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1442. Min Act: -0.0003

Data Index: 1131131 (C4 (Web Text))

Max Activating Token Index: 724

Text #8

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1446. Min Act: -0.0003

Data Index: 1156114 (C4 (Web Text))

Max Activating Token Index: 902

Text #9

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1430. Min Act: -0.0003

Data Index: 1316981 (C4 (Web Text))

Max Activating Token Index: 975

Text #10

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1427. Min Act: -0.0003

Data Index: 980561 (C4 (Web Text))

Max Activating Token Index: 728

Text #11

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1370. Min Act: -0.0003

Data Index: 234439 (C4 (Web Text))

Max Activating Token Index: 323

Text #12

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1403. Min Act: -0.0003

Data Index: 1000335 (C4 (Web Text))

Max Activating Token Index: 806

Text #13

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1447. Min Act: -0.0003

Data Index: 315582 (C4 (Web Text))

Max Activating Token Index: 818

Text #14

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1451. Min Act: -0.0003

Data Index: 394013 (C4 (Web Text))

Max Activating Token Index: 499

Text #15

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1389. Min Act: -0.0003

Data Index: 908773 (C4 (Web Text))

Max Activating Token Index: 448

Text #16

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1336. Min Act: -0.0003

Data Index: 1235219 (C4 (Web Text))

Max Activating Token Index: 138

Text #17

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1371. Min Act: -0.0003

Data Index: 11553 (C4 (Web Text))

Max Activating Token Index: 814

Text #18

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1216. Min Act: -0.0003

Data Index: 323728 (C4 (Web Text))

Max Activating Token Index: 816

Text #19

Max Range: 0.1564. Min Range: -0.1564

Max Act: 0.1461. Min Act: -0.0003

Data Index: 451791 (C4 (Web Text))

Max Activating Token Index: 838