Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 2029 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0920. Min Act: -0.0003

Data Index: 365298 (C4 (Web Text))

Max Activating Token Index: 778

Text #1

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0873. Min Act: -0.0003

Data Index: 188138 (C4 (Web Text))

Max Activating Token Index: 604

Text #2

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0779. Min Act: -0.0003

Data Index: 526183 (C4 (Web Text))

Max Activating Token Index: 698

Text #3

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0787. Min Act: -0.0003

Data Index: 78073 (C4 (Web Text))

Max Activating Token Index: 616

Text #4

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1255643 (C4 (Web Text))

Max Activating Token Index: 644

Text #5

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0731. Min Act: -0.0003

Data Index: 907154 (C4 (Web Text))

Max Activating Token Index: 695

Text #6

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0729. Min Act: -0.0003

Data Index: 1339658 (C4 (Web Text))

Max Activating Token Index: 931

Text #7

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0736. Min Act: -0.0003

Data Index: 656557 (C4 (Web Text))

Max Activating Token Index: 869

Text #8

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1061025 (C4 (Web Text))

Max Activating Token Index: 1011

Text #9

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0748. Min Act: -0.0003

Data Index: 260356 (C4 (Web Text))

Max Activating Token Index: 108

Text #10

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0724. Min Act: -0.0003

Data Index: 297334 (C4 (Web Text))

Max Activating Token Index: 143

Text #11

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0699. Min Act: -0.0003

Data Index: 763494 (C4 (Web Text))

Max Activating Token Index: 727

Text #12

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0723. Min Act: -0.0003

Data Index: 1050311 (C4 (Web Text))

Max Activating Token Index: 129

Text #13

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0698. Min Act: -0.0003

Data Index: 513311 (C4 (Web Text))

Max Activating Token Index: 930

Text #14

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0733. Min Act: -0.0003

Data Index: 1040646 (C4 (Web Text))

Max Activating Token Index: 900

Text #15

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0654. Min Act: -0.0002

Data Index: 751402 (C4 (Web Text))

Max Activating Token Index: 566

Text #16

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0711. Min Act: -0.0003

Data Index: 766299 (C4 (Web Text))

Max Activating Token Index: 462

Text #17

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0677. Min Act: -0.0003

Data Index: 1001117 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0692. Min Act: -0.0003

Data Index: 337663 (C4 (Web Text))

Max Activating Token Index: 258

Text #19

Max Range: 0.0920. Min Range: -0.0920

Max Act: 0.0695. Min Act: -0.0003

Data Index: 1049604 (C4 (Web Text))

Max Activating Token Index: 931