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

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

Neuron 3882 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: 0.0742. Min Range: -0.0742

Max Act: 0.0742. Min Act: -0.0002

Data Index: 280475 (C4 (Web Text))

Max Activating Token Index: 123

Text #1

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0628. Min Act: -0.0002

Data Index: 1322334 (C4 (Web Text))

Max Activating Token Index: 636

Text #2

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0719. Min Act: -0.0002

Data Index: 234830 (C4 (Web Text))

Max Activating Token Index: 187

Text #3

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0655. Min Act: -0.0002

Data Index: 327938 (C4 (Web Text))

Max Activating Token Index: 774

Text #4

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0672. Min Act: -0.0002

Data Index: 1084911 (C4 (Web Text))

Max Activating Token Index: 968

Text #5

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0600. Min Act: -0.0002

Data Index: 35845 (C4 (Web Text))

Max Activating Token Index: 769

Text #6

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0570. Min Act: -0.0002

Data Index: 1035608 (C4 (Web Text))

Max Activating Token Index: 766

Text #7

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0632. Min Act: -0.0002

Data Index: 748157 (C4 (Web Text))

Max Activating Token Index: 118

Text #8

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0663. Min Act: -0.0002

Data Index: 1030375 (C4 (Web Text))

Max Activating Token Index: 216

Text #9

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0589. Min Act: -0.0002

Data Index: 894759 (C4 (Web Text))

Max Activating Token Index: 29

Text #10

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0615. Min Act: -0.0002

Data Index: 967433 (C4 (Web Text))

Max Activating Token Index: 413

Text #11

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0548. Min Act: -0.0002

Data Index: 254462 (C4 (Web Text))

Max Activating Token Index: 729

Text #12

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0563. Min Act: -0.0002

Data Index: 1145937 (C4 (Web Text))

Max Activating Token Index: 918

Text #13

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0587. Min Act: -0.0002

Data Index: 400757 (C4 (Web Text))

Max Activating Token Index: 883

Text #14

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0601. Min Act: -0.0002

Data Index: 150470 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0598. Min Act: -0.0002

Data Index: 912000 (C4 (Web Text))

Max Activating Token Index: 305

Text #16

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1204933 (C4 (Web Text))

Max Activating Token Index: 956

Text #17

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0514. Min Act: -0.0002

Data Index: 1106575 (C4 (Web Text))

Max Activating Token Index: 664

Text #18

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0573. Min Act: -0.0002

Data Index: 1157983 (C4 (Web Text))

Max Activating Token Index: 55

Text #19

Max Range: 0.0742. Min Range: -0.0742

Max Act: 0.0531. Min Act: -0.0002

Data Index: 462640 (C4 (Web Text))

Max Activating Token Index: 1007