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

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

Neuron 2630 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.4556. Min Act: -0.0001

Data Index: 1173477 (C4 (Web Text))

Max Activating Token Index: 451

Text #1

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.2413. Min Act: -0.0001

Data Index: 330102 (C4 (Web Text))

Max Activating Token Index: 733

Text #2

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0954. Min Act: -0.0001

Data Index: 429482 (C4 (Web Text))

Max Activating Token Index: 1002

Text #3

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.1264. Min Act: -0.0001

Data Index: 1119572 (C4 (Web Text))

Max Activating Token Index: 843

Text #4

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0504. Min Act: -0.0001

Data Index: 477323 (C4 (Web Text))

Max Activating Token Index: 518

Text #5

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0176. Min Act: -0.0001

Data Index: 100461 (C4 (Web Text))

Max Activating Token Index: 499

Text #6

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0373. Min Act: -0.0001

Data Index: 292037 (C4 (Web Text))

Max Activating Token Index: 495

Text #7

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0111. Min Act: -0.0001

Data Index: 153687 (C4 (Web Text))

Max Activating Token Index: 953

Text #8

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0143. Min Act: -0.0001

Data Index: 1150874 (C4 (Web Text))

Max Activating Token Index: 490

Text #9

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0309. Min Act: -0.0001

Data Index: 1075806 (C4 (Web Text))

Max Activating Token Index: 782

Text #10

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0641. Min Act: -0.0001

Data Index: 695720 (C4 (Web Text))

Max Activating Token Index: 833

Text #11

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.9823. Min Act: -0.0001

Data Index: 454504 (C4 (Web Text))

Max Activating Token Index: 469

Text #12

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.9472. Min Act: -0.0001

Data Index: 1272435 (C4 (Web Text))

Max Activating Token Index: 991

Text #13

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0041. Min Act: -0.0001

Data Index: 629630 (C4 (Web Text))

Max Activating Token Index: 706

Text #14

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.9970. Min Act: -0.0001

Data Index: 993507 (C4 (Web Text))

Max Activating Token Index: 670

Text #15

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.9707. Min Act: -0.0001

Data Index: 196277 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 1.4556. Min Range: -1.4556

Max Act: 1.0164. Min Act: -0.0001

Data Index: 235537 (C4 (Web Text))

Max Activating Token Index: 642

Text #17

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.9764. Min Act: -0.0001

Data Index: 350633 (C4 (Web Text))

Max Activating Token Index: 140

Text #18

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.8609. Min Act: -0.0001

Data Index: 362706 (C4 (Web Text))

Max Activating Token Index: 68

Text #19

Max Range: 1.4556. Min Range: -1.4556

Max Act: 0.9746. Min Act: -0.0001

Data Index: 542642 (C4 (Web Text))

Max Activating Token Index: 506