Model: SoLU Model: 2 Layers, 2048 Neurons per Layer

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

Neuron 172 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-2l')

Text #0

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.1382. Min Act: -0.0003

Data Index: 760530 (C4 (Web Text))

Max Activating Token Index: 13

Text #1

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0852. Min Act: -0.0003

Data Index: 278436 (C4 (Web Text))

Max Activating Token Index: 40

Text #2

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0778. Min Act: -0.0004

Data Index: 1255509 (C4 (Web Text))

Max Activating Token Index: 869

Text #3

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0765. Min Act: -0.0003

Data Index: 774189 (C4 (Web Text))

Max Activating Token Index: 495

Text #4

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0741. Min Act: -0.0003

Data Index: 1138045 (C4 (Web Text))

Max Activating Token Index: 445

Text #5

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0733. Min Act: -0.0003

Data Index: 125396 (C4 (Web Text))

Max Activating Token Index: 560

Text #6

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0756. Min Act: -0.0003

Data Index: 50855 (C4 (Web Text))

Max Activating Token Index: 849

Text #7

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0735. Min Act: -0.0003

Data Index: 963655 (C4 (Web Text))

Max Activating Token Index: 585

Text #8

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0692. Min Act: -0.0003

Data Index: 1090775 (C4 (Web Text))

Max Activating Token Index: 567

Text #9

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0695. Min Act: -0.0003

Data Index: 37997 (C4 (Web Text))

Max Activating Token Index: 893

Text #10

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0614. Min Act: -0.0003

Data Index: 93896 (C4 (Web Text))

Max Activating Token Index: 337

Text #11

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0673. Min Act: -0.0003

Data Index: 267547 (C4 (Web Text))

Max Activating Token Index: 51

Text #12

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0643. Min Act: -0.0003

Data Index: 368662 (C4 (Web Text))

Max Activating Token Index: 281

Text #13

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0646. Min Act: -0.0003

Data Index: 297313 (C4 (Web Text))

Max Activating Token Index: 374

Text #14

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0615. Min Act: -0.0003

Data Index: 350687 (C4 (Web Text))

Max Activating Token Index: 746

Text #15

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0698. Min Act: -0.0003

Data Index: 1516404 (Python Code)

Max Activating Token Index: 348

Text #16

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0604. Min Act: -0.0003

Data Index: 1508456 (Python Code)

Max Activating Token Index: 343

Text #17

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0650. Min Act: -0.0003

Data Index: 1638816 (Python Code)

Max Activating Token Index: 824

Text #18

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0571. Min Act: -0.0003

Data Index: 101174 (C4 (Web Text))

Max Activating Token Index: 894

Text #19

Max Range: 0.1382. Min Range: -0.1382

Max Act: 0.0644. Min Act: -0.0003

Data Index: 474278 (C4 (Web Text))

Max Activating Token Index: 72