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

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

Neuron 4519 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: 0.0792. Min Range: -0.0792

Max Act: 0.0747. Min Act: -0.0002

Data Index: 862125 (C4 (Web Text))

Max Activating Token Index: 48

Text #1

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0767. Min Act: -0.0002

Data Index: 685410 (C4 (Web Text))

Max Activating Token Index: 7

Text #2

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0792. Min Act: -0.0002

Data Index: 198228 (C4 (Web Text))

Max Activating Token Index: 954

Text #3

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0782. Min Act: -0.0002

Data Index: 910805 (C4 (Web Text))

Max Activating Token Index: 833

Text #4

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0651. Min Act: -0.0002

Data Index: 1301545 (C4 (Web Text))

Max Activating Token Index: 733

Text #5

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0675. Min Act: -0.0002

Data Index: 248858 (C4 (Web Text))

Max Activating Token Index: 576

Text #6

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0579. Min Act: -0.0002

Data Index: 14663 (C4 (Web Text))

Max Activating Token Index: 171

Text #7

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0706. Min Act: -0.0002

Data Index: 1295814 (C4 (Web Text))

Max Activating Token Index: 35

Text #8

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0693. Min Act: -0.0002

Data Index: 1080817 (C4 (Web Text))

Max Activating Token Index: 763

Text #9

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0657. Min Act: -0.0002

Data Index: 754877 (C4 (Web Text))

Max Activating Token Index: 234

Text #10

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0619. Min Act: -0.0002

Data Index: 1112922 (C4 (Web Text))

Max Activating Token Index: 369

Text #11

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0716. Min Act: -0.0002

Data Index: 1275097 (C4 (Web Text))

Max Activating Token Index: 79

Text #12

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0556. Min Act: -0.0002

Data Index: 822640 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0668. Min Act: -0.0002

Data Index: 1314670 (C4 (Web Text))

Max Activating Token Index: 900

Text #14

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0730. Min Act: -0.0002

Data Index: 751258 (C4 (Web Text))

Max Activating Token Index: 356

Text #15

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0607. Min Act: -0.0002

Data Index: 652140 (C4 (Web Text))

Max Activating Token Index: 893

Text #16

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0587. Min Act: -0.0002

Data Index: 1111847 (C4 (Web Text))

Max Activating Token Index: 55

Text #17

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0626. Min Act: -0.0002

Data Index: 750734 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0591. Min Act: -0.0002

Data Index: 200654 (C4 (Web Text))

Max Activating Token Index: 773

Text #19

Max Range: 0.0792. Min Range: -0.0792

Max Act: 0.0676. Min Act: -0.0002

Data Index: 672365 (C4 (Web Text))

Max Activating Token Index: 764