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

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

Neuron 3452 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: 0.0787. Min Range: -0.0787

Max Act: 0.0747. Min Act: -0.0002

Data Index: 484266 (C4 (Web Text))

Max Activating Token Index: 90

Text #1

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0787. Min Act: -0.0002

Data Index: 106808 (C4 (Web Text))

Max Activating Token Index: 978

Text #2

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0632. Min Act: -0.0002

Data Index: 206691 (C4 (Web Text))

Max Activating Token Index: 687

Text #3

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0608. Min Act: -0.0002

Data Index: 486621 (C4 (Web Text))

Max Activating Token Index: 891

Text #4

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0630. Min Act: -0.0002

Data Index: 247866 (C4 (Web Text))

Max Activating Token Index: 754

Text #5

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0683. Min Act: -0.0002

Data Index: 1099528 (C4 (Web Text))

Max Activating Token Index: 584

Text #6

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0425. Min Act: -0.0002

Data Index: 341818 (C4 (Web Text))

Max Activating Token Index: 744

Text #7

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0649. Min Act: -0.0002

Data Index: 372602 (C4 (Web Text))

Max Activating Token Index: 348

Text #8

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0610. Min Act: -0.0002

Data Index: 346626 (C4 (Web Text))

Max Activating Token Index: 344

Text #9

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0620. Min Act: -0.0002

Data Index: 356423 (C4 (Web Text))

Max Activating Token Index: 256

Text #10

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0646. Min Act: -0.0002

Data Index: 1107227 (C4 (Web Text))

Max Activating Token Index: 371

Text #11

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0562. Min Act: -0.0002

Data Index: 842966 (C4 (Web Text))

Max Activating Token Index: 179

Text #12

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0605. Min Act: -0.0002

Data Index: 958838 (C4 (Web Text))

Max Activating Token Index: 951

Text #13

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0498. Min Act: -0.0002

Data Index: 795903 (C4 (Web Text))

Max Activating Token Index: 277

Text #14

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0538. Min Act: -0.0002

Data Index: 745823 (C4 (Web Text))

Max Activating Token Index: 82

Text #15

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0538. Min Act: -0.0002

Data Index: 769463 (C4 (Web Text))

Max Activating Token Index: 560

Text #16

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0555. Min Act: -0.0002

Data Index: 1019345 (C4 (Web Text))

Max Activating Token Index: 31

Text #17

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0501. Min Act: -0.0002

Data Index: 1115826 (C4 (Web Text))

Max Activating Token Index: 139

Text #18

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0437. Min Act: -0.0002

Data Index: 534808 (C4 (Web Text))

Max Activating Token Index: 674

Text #19

Max Range: 0.0787. Min Range: -0.0787

Max Act: 0.0546. Min Act: -0.0002

Data Index: 1151431 (C4 (Web Text))

Max Activating Token Index: 854