Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 503 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0697. Min Act: -0.0003

Data Index: 557348 (C4 (Web Text))

Max Activating Token Index: 751

Text #1

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0714. Min Act: -0.0003

Data Index: 474305 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0633. Min Act: -0.0002

Data Index: 1044138 (C4 (Web Text))

Max Activating Token Index: 246

Text #3

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0604. Min Act: -0.0003

Data Index: 482838 (C4 (Web Text))

Max Activating Token Index: 810

Text #4

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0588. Min Act: -0.0003

Data Index: 156466 (C4 (Web Text))

Max Activating Token Index: 859

Text #5

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0587. Min Act: -0.0003

Data Index: 991571 (C4 (Web Text))

Max Activating Token Index: 976

Text #6

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0617. Min Act: -0.0003

Data Index: 1212842 (C4 (Web Text))

Max Activating Token Index: 941

Text #7

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0624. Min Act: -0.0003

Data Index: 587134 (C4 (Web Text))

Max Activating Token Index: 21

Text #8

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1284605 (C4 (Web Text))

Max Activating Token Index: 184

Text #9

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0594. Min Act: -0.0003

Data Index: 1149531 (C4 (Web Text))

Max Activating Token Index: 709

Text #10

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0598. Min Act: -0.0003

Data Index: 1122229 (C4 (Web Text))

Max Activating Token Index: 924

Text #11

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0578. Min Act: -0.0003

Data Index: 1280289 (C4 (Web Text))

Max Activating Token Index: 938

Text #12

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0601. Min Act: -0.0003

Data Index: 443151 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0578. Min Act: -0.0002

Data Index: 780806 (C4 (Web Text))

Max Activating Token Index: 642

Text #14

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0572. Min Act: -0.0003

Data Index: 159296 (C4 (Web Text))

Max Activating Token Index: 794

Text #15

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0588. Min Act: -0.0003

Data Index: 491926 (C4 (Web Text))

Max Activating Token Index: 335

Text #16

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0586. Min Act: -0.0003

Data Index: 144732 (C4 (Web Text))

Max Activating Token Index: 754

Text #17

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0572. Min Act: -0.0003

Data Index: 163048 (C4 (Web Text))

Max Activating Token Index: 883

Text #18

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0573. Min Act: -0.0002

Data Index: 21076 (C4 (Web Text))

Max Activating Token Index: 817

Text #19

Max Range: 0.0714. Min Range: -0.0714

Max Act: 0.0580. Min Act: -0.0003

Data Index: 696048 (C4 (Web Text))

Max Activating Token Index: 312