Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1129 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0764. Min Act: -0.0005

Data Index: 1006806 (C4 (Web Text))

Max Activating Token Index: 92

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0005

Data Index: 949077 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0754. Min Act: -0.0005

Data Index: 907188 (C4 (Web Text))

Max Activating Token Index: 792

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0675. Min Act: -0.0005

Data Index: 743510 (C4 (Web Text))

Max Activating Token Index: 759

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0686. Min Act: -0.0005

Data Index: 864862 (C4 (Web Text))

Max Activating Token Index: 961

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0722. Min Act: -0.0005

Data Index: 968036 (C4 (Web Text))

Max Activating Token Index: 989

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0703. Min Act: -0.0005

Data Index: 716733 (C4 (Web Text))

Max Activating Token Index: 735

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0617. Min Act: -0.0005

Data Index: 220699 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0585. Min Act: -0.0005

Data Index: 1184610 (C4 (Web Text))

Max Activating Token Index: 1010

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0673. Min Act: -0.0005

Data Index: 1194737 (C4 (Web Text))

Max Activating Token Index: 429

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0646. Min Act: -0.0005

Data Index: 1122438 (C4 (Web Text))

Max Activating Token Index: 700

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0646. Min Act: -0.0005

Data Index: 375340 (C4 (Web Text))

Max Activating Token Index: 750

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0654. Min Act: -0.0005

Data Index: 1303730 (C4 (Web Text))

Max Activating Token Index: 910

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0653. Min Act: -0.0005

Data Index: 434233 (C4 (Web Text))

Max Activating Token Index: 764

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0641. Min Act: -0.0005

Data Index: 621023 (C4 (Web Text))

Max Activating Token Index: 631

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0635. Min Act: -0.0005

Data Index: 1411868 (Python Code)

Max Activating Token Index: 260

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0610. Min Act: -0.0005

Data Index: 902427 (C4 (Web Text))

Max Activating Token Index: 990

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0635. Min Act: -0.0005

Data Index: 1127186 (C4 (Web Text))

Max Activating Token Index: 772

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0572. Min Act: -0.0005

Data Index: 25279 (C4 (Web Text))

Max Activating Token Index: 756

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0664. Min Act: -0.0005

Data Index: 1306550 (C4 (Web Text))

Max Activating Token Index: 202