Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 403 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.4801. Min Act: -0.0000

Data Index: 781542 (C4 (Web Text))

Max Activating Token Index: 26

Text #1

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.4103. Min Act: -0.0000

Data Index: 47507 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3666. Min Act: -0.0000

Data Index: 965831 (C4 (Web Text))

Max Activating Token Index: 972

Text #3

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3792. Min Act: -0.0000

Data Index: 600256 (C4 (Web Text))

Max Activating Token Index: 965

Text #4

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3632. Min Act: -0.0000

Data Index: 986293 (C4 (Web Text))

Max Activating Token Index: 351

Text #5

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3667. Min Act: -0.0000

Data Index: 929992 (C4 (Web Text))

Max Activating Token Index: 704

Text #6

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3628. Min Act: -0.0000

Data Index: 809557 (C4 (Web Text))

Max Activating Token Index: 561

Text #7

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3602. Min Act: -0.0000

Data Index: 619174 (C4 (Web Text))

Max Activating Token Index: 957

Text #8

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3708. Min Act: -0.0000

Data Index: 727501 (C4 (Web Text))

Max Activating Token Index: 872

Text #9

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3590. Min Act: -0.0000

Data Index: 94737 (C4 (Web Text))

Max Activating Token Index: 1010

Text #10

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3576. Min Act: -0.0000

Data Index: 151444 (C4 (Web Text))

Max Activating Token Index: 900

Text #11

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3551. Min Act: -0.0000

Data Index: 173226 (C4 (Web Text))

Max Activating Token Index: 772

Text #12

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1050686 (C4 (Web Text))

Max Activating Token Index: 748

Text #13

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3499. Min Act: -0.0000

Data Index: 290820 (C4 (Web Text))

Max Activating Token Index: 648

Text #14

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3595. Min Act: -0.0000

Data Index: 226559 (C4 (Web Text))

Max Activating Token Index: 860

Text #15

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3609. Min Act: -0.0000

Data Index: 436771 (C4 (Web Text))

Max Activating Token Index: 493

Text #16

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3501. Min Act: -0.0000

Data Index: 296543 (C4 (Web Text))

Max Activating Token Index: 719

Text #17

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3548. Min Act: -0.0000

Data Index: 601949 (C4 (Web Text))

Max Activating Token Index: 755

Text #18

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3846. Min Act: -0.0000

Data Index: 300828 (C4 (Web Text))

Max Activating Token Index: 920

Text #19

Max Range: 0.4801. Min Range: -0.4801

Max Act: 0.3585. Min Act: -0.0000

Data Index: 89418 (C4 (Web Text))

Max Activating Token Index: 801