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

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

Neuron 1040 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: 0.0866. Min Range: -0.0866

Max Act: 0.0866. Min Act: -0.0002

Data Index: 826934 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0721. Min Act: -0.0002

Data Index: 491657 (C4 (Web Text))

Max Activating Token Index: 879

Text #2

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0664. Min Act: -0.0002

Data Index: 360782 (C4 (Web Text))

Max Activating Token Index: 671

Text #3

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0724. Min Act: -0.0002

Data Index: 339910 (C4 (Web Text))

Max Activating Token Index: 691

Text #4

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0714. Min Act: -0.0002

Data Index: 846695 (C4 (Web Text))

Max Activating Token Index: 553

Text #5

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0602. Min Act: -0.0002

Data Index: 1195939 (C4 (Web Text))

Max Activating Token Index: 1022

Text #6

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0623. Min Act: -0.0002

Data Index: 999984 (C4 (Web Text))

Max Activating Token Index: 23

Text #7

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0643. Min Act: -0.0002

Data Index: 695789 (C4 (Web Text))

Max Activating Token Index: 837

Text #8

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0625. Min Act: -0.0002

Data Index: 1340610 (C4 (Web Text))

Max Activating Token Index: 893

Text #9

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0587. Min Act: -0.0002

Data Index: 872946 (C4 (Web Text))

Max Activating Token Index: 779

Text #10

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0613. Min Act: -0.0002

Data Index: 465358 (C4 (Web Text))

Max Activating Token Index: 111

Text #11

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0626. Min Act: -0.0002

Data Index: 318154 (C4 (Web Text))

Max Activating Token Index: 565

Text #12

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0529. Min Act: -0.0002

Data Index: 1315749 (C4 (Web Text))

Max Activating Token Index: 629

Text #13

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0569. Min Act: -0.0002

Data Index: 1162003 (C4 (Web Text))

Max Activating Token Index: 55

Text #14

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0526. Min Act: -0.0002

Data Index: 712550 (C4 (Web Text))

Max Activating Token Index: 785

Text #15

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0561. Min Act: -0.0002

Data Index: 909536 (C4 (Web Text))

Max Activating Token Index: 233

Text #16

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0544. Min Act: -0.0002

Data Index: 1006033 (C4 (Web Text))

Max Activating Token Index: 657

Text #17

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0593. Min Act: -0.0002

Data Index: 619700 (C4 (Web Text))

Max Activating Token Index: 573

Text #18

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0555. Min Act: -0.0002

Data Index: 752903 (C4 (Web Text))

Max Activating Token Index: 717

Text #19

Max Range: 0.0866. Min Range: -0.0866

Max Act: 0.0574. Min Act: -0.0002

Data Index: 928553 (C4 (Web Text))

Max Activating Token Index: 685