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

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

Neuron 776 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: 0.0759. Min Range: -0.0759

Max Act: 0.0759. Min Act: -0.0004

Data Index: 79425 (C4 (Web Text))

Max Activating Token Index: 173

Text #1

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0744. Min Act: -0.0003

Data Index: 976320 (C4 (Web Text))

Max Activating Token Index: 373

Text #2

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0730. Min Act: -0.0003

Data Index: 992077 (C4 (Web Text))

Max Activating Token Index: 75

Text #3

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0720. Min Act: -0.0004

Data Index: 90391 (C4 (Web Text))

Max Activating Token Index: 986

Text #4

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0699. Min Act: -0.0003

Data Index: 923144 (C4 (Web Text))

Max Activating Token Index: 523

Text #5

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0690. Min Act: -0.0003

Data Index: 190188 (C4 (Web Text))

Max Activating Token Index: 64

Text #6

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0687. Min Act: -0.0003

Data Index: 1160431 (C4 (Web Text))

Max Activating Token Index: 448

Text #7

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0673. Min Act: -0.0003

Data Index: 589515 (C4 (Web Text))

Max Activating Token Index: 478

Text #8

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0677. Min Act: -0.0003

Data Index: 323692 (C4 (Web Text))

Max Activating Token Index: 389

Text #9

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0707. Min Act: -0.0004

Data Index: 1224280 (C4 (Web Text))

Max Activating Token Index: 34

Text #10

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0669. Min Act: -0.0003

Data Index: 1270974 (C4 (Web Text))

Max Activating Token Index: 609

Text #11

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0674. Min Act: -0.0004

Data Index: 546659 (C4 (Web Text))

Max Activating Token Index: 948

Text #12

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0671. Min Act: -0.0003

Data Index: 724730 (C4 (Web Text))

Max Activating Token Index: 418

Text #13

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0666. Min Act: -0.0003

Data Index: 227870 (C4 (Web Text))

Max Activating Token Index: 628

Text #14

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0662. Min Act: -0.0003

Data Index: 588695 (C4 (Web Text))

Max Activating Token Index: 428

Text #15

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0656. Min Act: -0.0003

Data Index: 188906 (C4 (Web Text))

Max Activating Token Index: 918

Text #16

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0643. Min Act: -0.0003

Data Index: 884960 (C4 (Web Text))

Max Activating Token Index: 532

Text #17

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0636. Min Act: -0.0004

Data Index: 830207 (C4 (Web Text))

Max Activating Token Index: 145

Text #18

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0645. Min Act: -0.0003

Data Index: 1247904 (C4 (Web Text))

Max Activating Token Index: 29

Text #19

Max Range: 0.0759. Min Range: -0.0759

Max Act: 0.0630. Min Act: -0.0003

Data Index: 621931 (C4 (Web Text))

Max Activating Token Index: 490