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

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

Neuron 818 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: 1.3857. Min Range: -1.3857

Max Act: 1.3857. Min Act: -0.0000

Data Index: 792872 (C4 (Web Text))

Max Activating Token Index: 678

Text #1

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2684. Min Act: -0.0000

Data Index: 1112758 (C4 (Web Text))

Max Activating Token Index: 929

Text #2

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.2516. Min Act: -0.0000

Data Index: 452368 (C4 (Web Text))

Max Activating Token Index: 27

Text #3

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.3109. Min Act: -0.0000

Data Index: 1058664 (C4 (Web Text))

Max Activating Token Index: 238

Text #4

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1971. Min Act: -0.0000

Data Index: 1210652 (C4 (Web Text))

Max Activating Token Index: 450

Text #5

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1691. Min Act: -0.0000

Data Index: 1240475 (C4 (Web Text))

Max Activating Token Index: 169

Text #6

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0578. Min Act: -0.0000

Data Index: 319878 (C4 (Web Text))

Max Activating Token Index: 175

Text #7

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0558. Min Act: -0.0000

Data Index: 805191 (C4 (Web Text))

Max Activating Token Index: 533

Text #8

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1025. Min Act: -0.0000

Data Index: 635072 (C4 (Web Text))

Max Activating Token Index: 611

Text #9

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1633. Min Act: -0.0000

Data Index: 662136 (C4 (Web Text))

Max Activating Token Index: 911

Text #10

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1451. Min Act: -0.0000

Data Index: 107918 (C4 (Web Text))

Max Activating Token Index: 99

Text #11

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.1229. Min Act: -0.0000

Data Index: 1285523 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0250. Min Act: -0.0000

Data Index: 997553 (C4 (Web Text))

Max Activating Token Index: 497

Text #13

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9458. Min Act: -0.0000

Data Index: 567479 (C4 (Web Text))

Max Activating Token Index: 847

Text #14

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0362. Min Act: -0.0000

Data Index: 139773 (C4 (Web Text))

Max Activating Token Index: 40

Text #15

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9467. Min Act: -0.0000

Data Index: 1384 (C4 (Web Text))

Max Activating Token Index: 216

Text #16

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9641. Min Act: -0.0000

Data Index: 733398 (C4 (Web Text))

Max Activating Token Index: 1007

Text #17

Max Range: 1.3857. Min Range: -1.3857

Max Act: 1.0584. Min Act: -0.0000

Data Index: 762749 (C4 (Web Text))

Max Activating Token Index: 874

Text #18

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9587. Min Act: -0.0000

Data Index: 1548853 (Python Code)

Max Activating Token Index: 292

Text #19

Max Range: 1.3857. Min Range: -1.3857

Max Act: 0.9830. Min Act: -0.0000

Data Index: 286098 (C4 (Web Text))

Max Activating Token Index: 40