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

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

Neuron 1501 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0642. Min Act: -0.0002

Data Index: 818823 (C4 (Web Text))

Max Activating Token Index: 900

Text #1

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0653. Min Act: -0.0002

Data Index: 545194 (C4 (Web Text))

Max Activating Token Index: 382

Text #2

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9687. Min Act: -0.0002

Data Index: 776985 (C4 (Web Text))

Max Activating Token Index: 983

Text #3

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0022. Min Act: -0.0002

Data Index: 867925 (C4 (Web Text))

Max Activating Token Index: 68

Text #4

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9357. Min Act: -0.0002

Data Index: 398379 (C4 (Web Text))

Max Activating Token Index: 816

Text #5

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0223. Min Act: -0.0002

Data Index: 63309 (C4 (Web Text))

Max Activating Token Index: 828

Text #6

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0556. Min Act: -0.0002

Data Index: 835877 (C4 (Web Text))

Max Activating Token Index: 896

Text #7

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8540. Min Act: -0.0002

Data Index: 237773 (C4 (Web Text))

Max Activating Token Index: 414

Text #8

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0476. Min Act: -0.0002

Data Index: 422996 (C4 (Web Text))

Max Activating Token Index: 823

Text #9

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9001. Min Act: -0.0002

Data Index: 87545 (C4 (Web Text))

Max Activating Token Index: 891

Text #10

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9733. Min Act: -0.0002

Data Index: 126670 (C4 (Web Text))

Max Activating Token Index: 806

Text #11

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9350. Min Act: -0.0002

Data Index: 752153 (C4 (Web Text))

Max Activating Token Index: 961

Text #12

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8765. Min Act: -0.0002

Data Index: 1065671 (C4 (Web Text))

Max Activating Token Index: 778

Text #13

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9697. Min Act: -0.0002

Data Index: 295507 (C4 (Web Text))

Max Activating Token Index: 5

Text #14

Max Range: 1.0653. Min Range: -1.0653

Max Act: 1.0219. Min Act: -0.0002

Data Index: 1163027 (C4 (Web Text))

Max Activating Token Index: 805

Text #15

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8500. Min Act: -0.0002

Data Index: 996041 (C4 (Web Text))

Max Activating Token Index: 824

Text #16

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8948. Min Act: -0.0002

Data Index: 25552 (C4 (Web Text))

Max Activating Token Index: 860

Text #17

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9758. Min Act: -0.0002

Data Index: 785182 (C4 (Web Text))

Max Activating Token Index: 638

Text #18

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.8471. Min Act: -0.0002

Data Index: 921732 (C4 (Web Text))

Max Activating Token Index: 567

Text #19

Max Range: 1.0653. Min Range: -1.0653

Max Act: 0.9699. Min Act: -0.0002

Data Index: 1234980 (C4 (Web Text))

Max Activating Token Index: 769