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

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

Neuron 148 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1110. Min Range: -1.1110

Max Act: 1.1110. Min Act: -0.0000

Data Index: 1327933 (C4 (Web Text))

Max Activating Token Index: 359

Text #1

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.8405. Min Act: -0.0000

Data Index: 11216 (C4 (Web Text))

Max Activating Token Index: 315

Text #2

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.8668. Min Act: -0.0000

Data Index: 525709 (C4 (Web Text))

Max Activating Token Index: 895

Text #3

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7242. Min Act: -0.0000

Data Index: 299813 (C4 (Web Text))

Max Activating Token Index: 148

Text #4

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.8024. Min Act: -0.0000

Data Index: 1131491 (C4 (Web Text))

Max Activating Token Index: 48

Text #5

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.8458. Min Act: -0.0000

Data Index: 1192629 (C4 (Web Text))

Max Activating Token Index: 327

Text #6

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7807. Min Act: -0.0000

Data Index: 1298087 (C4 (Web Text))

Max Activating Token Index: 503

Text #7

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7505. Min Act: -0.0000

Data Index: 612155 (C4 (Web Text))

Max Activating Token Index: 763

Text #8

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7507. Min Act: -0.0000

Data Index: 440875 (C4 (Web Text))

Max Activating Token Index: 997

Text #9

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7507. Min Act: -0.0000

Data Index: 649542 (C4 (Web Text))

Max Activating Token Index: 519

Text #10

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7337. Min Act: -0.0000

Data Index: 828940 (C4 (Web Text))

Max Activating Token Index: 27

Text #11

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7325. Min Act: -0.0000

Data Index: 219134 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.7460. Min Act: -0.0000

Data Index: 845795 (C4 (Web Text))

Max Activating Token Index: 79

Text #13

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6863. Min Act: -0.0000

Data Index: 389916 (C4 (Web Text))

Max Activating Token Index: 69

Text #14

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6700. Min Act: -0.0000

Data Index: 1195841 (C4 (Web Text))

Max Activating Token Index: 48

Text #15

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6694. Min Act: -0.0000

Data Index: 784924 (C4 (Web Text))

Max Activating Token Index: 301

Text #16

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6640. Min Act: -0.0000

Data Index: 1079472 (C4 (Web Text))

Max Activating Token Index: 599

Text #17

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6657. Min Act: -0.0000

Data Index: 631885 (C4 (Web Text))

Max Activating Token Index: 949

Text #18

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6843. Min Act: -0.0000

Data Index: 409906 (C4 (Web Text))

Max Activating Token Index: 979

Text #19

Max Range: 1.1110. Min Range: -1.1110

Max Act: 0.6639. Min Act: -0.0000

Data Index: 628699 (C4 (Web Text))

Max Activating Token Index: 490