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

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

Neuron 1599 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: 0.0789. Min Range: -0.0789

Max Act: 0.0715. Min Act: -0.0002

Data Index: 540677 (C4 (Web Text))

Max Activating Token Index: 190

Text #1

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0682. Min Act: -0.0002

Data Index: 1255345 (C4 (Web Text))

Max Activating Token Index: 44

Text #2

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0697. Min Act: -0.0002

Data Index: 893288 (C4 (Web Text))

Max Activating Token Index: 638

Text #3

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0691. Min Act: -0.0002

Data Index: 343003 (C4 (Web Text))

Max Activating Token Index: 900

Text #4

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0621. Min Act: -0.0002

Data Index: 1102833 (C4 (Web Text))

Max Activating Token Index: 166

Text #5

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0789. Min Act: -0.0002

Data Index: 492491 (C4 (Web Text))

Max Activating Token Index: 902

Text #6

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0713. Min Act: -0.0002

Data Index: 1200883 (C4 (Web Text))

Max Activating Token Index: 920

Text #7

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0752. Min Act: -0.0002

Data Index: 1058491 (C4 (Web Text))

Max Activating Token Index: 831

Text #8

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0475. Min Act: -0.0002

Data Index: 376466 (C4 (Web Text))

Max Activating Token Index: 737

Text #9

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0616. Min Act: -0.0002

Data Index: 107787 (C4 (Web Text))

Max Activating Token Index: 573

Text #10

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0680. Min Act: -0.0002

Data Index: 1072875 (C4 (Web Text))

Max Activating Token Index: 61

Text #11

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0680. Min Act: -0.0002

Data Index: 57713 (C4 (Web Text))

Max Activating Token Index: 960

Text #12

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0623. Min Act: -0.0002

Data Index: 984200 (C4 (Web Text))

Max Activating Token Index: 364

Text #13

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0631. Min Act: -0.0002

Data Index: 1041673 (C4 (Web Text))

Max Activating Token Index: 524

Text #14

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0687. Min Act: -0.0002

Data Index: 1065024 (C4 (Web Text))

Max Activating Token Index: 77

Text #15

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0700. Min Act: -0.0002

Data Index: 839259 (C4 (Web Text))

Max Activating Token Index: 906

Text #16

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0642. Min Act: -0.0002

Data Index: 126406 (C4 (Web Text))

Max Activating Token Index: 233

Text #17

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0500. Min Act: -0.0002

Data Index: 19224 (C4 (Web Text))

Max Activating Token Index: 386

Text #18

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0642. Min Act: -0.0002

Data Index: 451032 (C4 (Web Text))

Max Activating Token Index: 54

Text #19

Max Range: 0.0789. Min Range: -0.0789

Max Act: 0.0663. Min Act: -0.0002

Data Index: 418943 (C4 (Web Text))

Max Activating Token Index: 436