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

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

Neuron 5020 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0684. Min Act: -0.0003

Data Index: 1124941 (C4 (Web Text))

Max Activating Token Index: 683

Text #1

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0672. Min Act: -0.0003

Data Index: 167520 (C4 (Web Text))

Max Activating Token Index: 751

Text #2

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0675. Min Act: -0.0002

Data Index: 1262933 (C4 (Web Text))

Max Activating Token Index: 591

Text #3

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0653. Min Act: -0.0002

Data Index: 475461 (C4 (Web Text))

Max Activating Token Index: 37

Text #4

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0628. Min Act: -0.0003

Data Index: 972380 (C4 (Web Text))

Max Activating Token Index: 662

Text #5

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0620. Min Act: -0.0003

Data Index: 343203 (C4 (Web Text))

Max Activating Token Index: 331

Text #6

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0597. Min Act: -0.0002

Data Index: 684292 (C4 (Web Text))

Max Activating Token Index: 562

Text #7

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0626. Min Act: -0.0002

Data Index: 1188855 (C4 (Web Text))

Max Activating Token Index: 753

Text #8

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0615. Min Act: -0.0003

Data Index: 44595 (C4 (Web Text))

Max Activating Token Index: 766

Text #9

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0606. Min Act: -0.0003

Data Index: 157385 (C4 (Web Text))

Max Activating Token Index: 548

Text #10

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0597. Min Act: -0.0003

Data Index: 448047 (C4 (Web Text))

Max Activating Token Index: 3

Text #11

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0591. Min Act: -0.0002

Data Index: 47272 (C4 (Web Text))

Max Activating Token Index: 479

Text #12

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0591. Min Act: -0.0003

Data Index: 75997 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0586. Min Act: -0.0003

Data Index: 806775 (C4 (Web Text))

Max Activating Token Index: 698

Text #14

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0585. Min Act: -0.0003

Data Index: 689626 (C4 (Web Text))

Max Activating Token Index: 252

Text #15

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0586. Min Act: -0.0003

Data Index: 926683 (C4 (Web Text))

Max Activating Token Index: 402

Text #16

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0582. Min Act: -0.0003

Data Index: 1189226 (C4 (Web Text))

Max Activating Token Index: 849

Text #17

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0582. Min Act: -0.0003

Data Index: 715234 (C4 (Web Text))

Max Activating Token Index: 15

Text #18

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0581. Min Act: -0.0003

Data Index: 883129 (C4 (Web Text))

Max Activating Token Index: 75

Text #19

Max Range: 0.0684. Min Range: -0.0684

Max Act: 0.0588. Min Act: -0.0003

Data Index: 996790 (C4 (Web Text))

Max Activating Token Index: 811