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

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

Neuron 4456 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: 0.0912. Min Range: -0.0912

Max Act: 0.0860. Min Act: -0.0002

Data Index: 571554 (C4 (Web Text))

Max Activating Token Index: 463

Text #1

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0860. Min Act: -0.0002

Data Index: 601447 (C4 (Web Text))

Max Activating Token Index: 720

Text #2

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0912. Min Act: -0.0002

Data Index: 771919 (C4 (Web Text))

Max Activating Token Index: 259

Text #3

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0799. Min Act: -0.0002

Data Index: 1222716 (C4 (Web Text))

Max Activating Token Index: 511

Text #4

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0707. Min Act: -0.0002

Data Index: 561083 (C4 (Web Text))

Max Activating Token Index: 883

Text #5

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0720. Min Act: -0.0002

Data Index: 1010538 (C4 (Web Text))

Max Activating Token Index: 797

Text #6

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0715. Min Act: -0.0002

Data Index: 1033777 (C4 (Web Text))

Max Activating Token Index: 730

Text #7

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0637. Min Act: -0.0002

Data Index: 347930 (C4 (Web Text))

Max Activating Token Index: 374

Text #8

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0674. Min Act: -0.0002

Data Index: 327882 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0630. Min Act: -0.0003

Data Index: 1335523 (C4 (Web Text))

Max Activating Token Index: 580

Text #10

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0562. Min Act: -0.0002

Data Index: 69779 (C4 (Web Text))

Max Activating Token Index: 940

Text #11

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0586. Min Act: -0.0002

Data Index: 1355918 (C4 (Web Text))

Max Activating Token Index: 612

Text #12

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1279243 (C4 (Web Text))

Max Activating Token Index: 48

Text #13

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0650. Min Act: -0.0002

Data Index: 880594 (C4 (Web Text))

Max Activating Token Index: 969

Text #14

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0572. Min Act: -0.0002

Data Index: 1044801 (C4 (Web Text))

Max Activating Token Index: 837

Text #15

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0488. Min Act: -0.0002

Data Index: 329911 (C4 (Web Text))

Max Activating Token Index: 722

Text #16

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0603. Min Act: -0.0002

Data Index: 1129165 (C4 (Web Text))

Max Activating Token Index: 988

Text #17

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0539. Min Act: -0.0002

Data Index: 291755 (C4 (Web Text))

Max Activating Token Index: 581

Text #18

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0483. Min Act: -0.0002

Data Index: 1165431 (C4 (Web Text))

Max Activating Token Index: 776

Text #19

Max Range: 0.0912. Min Range: -0.0912

Max Act: 0.0527. Min Act: -0.0002

Data Index: 1331745 (C4 (Web Text))

Max Activating Token Index: 73