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

Dataset: The Pile

Neuron 45 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.4446. Min Act: -0.0000

Data Index: 1682522 (The Pile)

Max Activating Token Index: 152

Text #1

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.3084. Min Act: -0.0000

Data Index: 26845 (The Pile)

Max Activating Token Index: 566

Text #2

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1689. Min Act: -0.0000

Data Index: 266018 (The Pile)

Max Activating Token Index: 914

Text #3

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.0800. Min Act: -0.0000

Data Index: 1527305 (The Pile)

Max Activating Token Index: 615

Text #4

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.0550. Min Act: -0.0000

Data Index: 651608 (The Pile)

Max Activating Token Index: 535

Text #5

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1024. Min Act: -0.0000

Data Index: 244469 (The Pile)

Max Activating Token Index: 675

Text #6

Max Range: 1.4446. Min Range: -1.4446

Max Act: 1.1138. Min Act: -0.0000

Data Index: 773304 (The Pile)

Max Activating Token Index: 853

Text #7

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.9575. Min Act: -0.0000

Data Index: 63248 (The Pile)

Max Activating Token Index: 478

Text #8

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.9664. Min Act: -0.0000

Data Index: 1248241 (The Pile)

Max Activating Token Index: 459

Text #9

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.9291. Min Act: -0.0000

Data Index: 473706 (The Pile)

Max Activating Token Index: 568

Text #10

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8939. Min Act: -0.0000

Data Index: 1179751 (The Pile)

Max Activating Token Index: 980

Text #11

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.9173. Min Act: -0.0000

Data Index: 539218 (The Pile)

Max Activating Token Index: 654

Text #12

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8741. Min Act: -0.0000

Data Index: 671993 (The Pile)

Max Activating Token Index: 662

Text #13

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8907. Min Act: -0.0000

Data Index: 1268456 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8868. Min Act: 0.0000

Data Index: 1600139 (The Pile)

Max Activating Token Index: 306

Text #15

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8356. Min Act: 0.0000

Data Index: 955782 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8083. Min Act: 0.0001

Data Index: 410600 (The Pile)

Max Activating Token Index: 932

Text #17

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.8976. Min Act: -0.0000

Data Index: 571379 (The Pile)

Max Activating Token Index: 466

Text #18

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.7909. Min Act: -0.0000

Data Index: 110579 (The Pile)

Max Activating Token Index: 228

Text #19

Max Range: 1.4446. Min Range: -1.4446

Max Act: 0.7859. Min Act: -0.0000

Data Index: 742212 (The Pile)

Max Activating Token Index: 1015