Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 43 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0914. Min Act: -0.0003

Data Index: 1295256 (C4 (Web Text))

Max Activating Token Index: 950

Text #1

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0870. Min Act: -0.0003

Data Index: 543670 (C4 (Web Text))

Max Activating Token Index: 738

Text #2

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0819. Min Act: -0.0003

Data Index: 770211 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0765. Min Act: -0.0003

Data Index: 1258666 (C4 (Web Text))

Max Activating Token Index: 777

Text #4

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0792. Min Act: -0.0003

Data Index: 458765 (C4 (Web Text))

Max Activating Token Index: 84

Text #5

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0781. Min Act: -0.0003

Data Index: 725677 (C4 (Web Text))

Max Activating Token Index: 753

Text #6

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0760. Min Act: -0.0003

Data Index: 1186928 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0744. Min Act: -0.0003

Data Index: 574453 (C4 (Web Text))

Max Activating Token Index: 173

Text #8

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0755. Min Act: -0.0003

Data Index: 632541 (C4 (Web Text))

Max Activating Token Index: 783

Text #9

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0835. Min Act: -0.0003

Data Index: 453442 (C4 (Web Text))

Max Activating Token Index: 650

Text #10

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0720. Min Act: -0.0004

Data Index: 538932 (C4 (Web Text))

Max Activating Token Index: 51

Text #11

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0707. Min Act: -0.0003

Data Index: 956930 (C4 (Web Text))

Max Activating Token Index: 765

Text #12

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0731. Min Act: -0.0003

Data Index: 1527314 (Python Code)

Max Activating Token Index: 768

Text #13

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0772. Min Act: -0.0003

Data Index: 367734 (C4 (Web Text))

Max Activating Token Index: 255

Text #14

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0728. Min Act: -0.0003

Data Index: 540698 (C4 (Web Text))

Max Activating Token Index: 604

Text #15

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0754. Min Act: -0.0003

Data Index: 129771 (C4 (Web Text))

Max Activating Token Index: 848

Text #16

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0767. Min Act: -0.0004

Data Index: 45143 (C4 (Web Text))

Max Activating Token Index: 900

Text #17

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0664. Min Act: -0.0003

Data Index: 916799 (C4 (Web Text))

Max Activating Token Index: 648

Text #18

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0735. Min Act: -0.0003

Data Index: 1314743 (C4 (Web Text))

Max Activating Token Index: 289

Text #19

Max Range: 0.0914. Min Range: -0.0914

Max Act: 0.0714. Min Act: -0.0003

Data Index: 539389 (C4 (Web Text))

Max Activating Token Index: 618