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

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

Neuron 3245 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: 0.0794. Min Range: -0.0794

Max Act: 0.0794. Min Act: -0.0002

Data Index: 491900 (C4 (Web Text))

Max Activating Token Index: 817

Text #1

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0749. Min Act: -0.0002

Data Index: 1206255 (C4 (Web Text))

Max Activating Token Index: 33

Text #2

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0725. Min Act: -0.0002

Data Index: 1164234 (C4 (Web Text))

Max Activating Token Index: 496

Text #3

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0690. Min Act: -0.0002

Data Index: 581144 (C4 (Web Text))

Max Activating Token Index: 827

Text #4

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0668. Min Act: -0.0002

Data Index: 451954 (C4 (Web Text))

Max Activating Token Index: 99

Text #5

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0617. Min Act: -0.0002

Data Index: 454720 (C4 (Web Text))

Max Activating Token Index: 816

Text #6

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0606. Min Act: -0.0002

Data Index: 14110 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0623. Min Act: -0.0002

Data Index: 234661 (C4 (Web Text))

Max Activating Token Index: 485

Text #8

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0599. Min Act: -0.0002

Data Index: 869548 (C4 (Web Text))

Max Activating Token Index: 51

Text #9

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0580. Min Act: -0.0002

Data Index: 1193330 (C4 (Web Text))

Max Activating Token Index: 688

Text #10

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0623. Min Act: -0.0002

Data Index: 514256 (C4 (Web Text))

Max Activating Token Index: 993

Text #11

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0608. Min Act: -0.0002

Data Index: 797192 (C4 (Web Text))

Max Activating Token Index: 160

Text #12

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0614. Min Act: -0.0002

Data Index: 260682 (C4 (Web Text))

Max Activating Token Index: 968

Text #13

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0607. Min Act: -0.0002

Data Index: 1261672 (C4 (Web Text))

Max Activating Token Index: 248

Text #14

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0608. Min Act: -0.0002

Data Index: 612519 (C4 (Web Text))

Max Activating Token Index: 918

Text #15

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0653. Min Act: -0.0002

Data Index: 527620 (C4 (Web Text))

Max Activating Token Index: 528

Text #16

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0602. Min Act: -0.0002

Data Index: 168141 (C4 (Web Text))

Max Activating Token Index: 356

Text #17

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0625. Min Act: -0.0002

Data Index: 515887 (C4 (Web Text))

Max Activating Token Index: 623

Text #18

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0597. Min Act: -0.0002

Data Index: 575077 (C4 (Web Text))

Max Activating Token Index: 44

Text #19

Max Range: 0.0794. Min Range: -0.0794

Max Act: 0.0598. Min Act: -0.0002

Data Index: 1358913 (C4 (Web Text))

Max Activating Token Index: 90