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

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

Neuron 747 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.2719. Min Act: -0.0001

Data Index: 597206 (C4 (Web Text))

Max Activating Token Index: 429

Text #1

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.2054. Min Act: -0.0001

Data Index: 1531285 (Python Code)

Max Activating Token Index: 881

Text #2

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0891. Min Act: -0.0001

Data Index: 869899 (C4 (Web Text))

Max Activating Token Index: 753

Text #3

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.2042. Min Act: -0.0001

Data Index: 1434409 (Python Code)

Max Activating Token Index: 677

Text #4

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.1576. Min Act: -0.0001

Data Index: 548764 (C4 (Web Text))

Max Activating Token Index: 1004

Text #5

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.1895. Min Act: -0.0001

Data Index: 1055710 (C4 (Web Text))

Max Activating Token Index: 114

Text #6

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0107. Min Act: -0.0001

Data Index: 637730 (C4 (Web Text))

Max Activating Token Index: 1009

Text #7

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0160. Min Act: -0.0001

Data Index: 633008 (C4 (Web Text))

Max Activating Token Index: 851

Text #8

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0398. Min Act: -0.0001

Data Index: 5852 (C4 (Web Text))

Max Activating Token Index: 805

Text #9

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0004. Min Act: -0.0001

Data Index: 1321282 (C4 (Web Text))

Max Activating Token Index: 389

Text #10

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9416. Min Act: -0.0001

Data Index: 1490968 (Python Code)

Max Activating Token Index: 37

Text #11

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0594. Min Act: -0.0001

Data Index: 660402 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9888. Min Act: -0.0001

Data Index: 845995 (C4 (Web Text))

Max Activating Token Index: 998

Text #13

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9843. Min Act: -0.0001

Data Index: 1003846 (C4 (Web Text))

Max Activating Token Index: 765

Text #14

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9546. Min Act: -0.0001

Data Index: 34569 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0536. Min Act: -0.0001

Data Index: 292815 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0833. Min Act: -0.0001

Data Index: 1389724 (Python Code)

Max Activating Token Index: 63

Text #17

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0502. Min Act: -0.0001

Data Index: 908955 (C4 (Web Text))

Max Activating Token Index: 392

Text #18

Max Range: 1.2719. Min Range: -1.2719

Max Act: 1.0429. Min Act: -0.0001

Data Index: 1111870 (C4 (Web Text))

Max Activating Token Index: 47

Text #19

Max Range: 1.2719. Min Range: -1.2719

Max Act: 0.9474. Min Act: -0.0001

Data Index: 238591 (C4 (Web Text))

Max Activating Token Index: 660