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

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

Neuron 746 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0831. Min Act: -0.0002

Data Index: 511422 (C4 (Web Text))

Max Activating Token Index: 717

Text #1

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0746. Min Act: -0.0002

Data Index: 182293 (C4 (Web Text))

Max Activating Token Index: 72

Text #2

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0730. Min Act: -0.0003

Data Index: 434872 (C4 (Web Text))

Max Activating Token Index: 36

Text #3

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0730. Min Act: -0.0003

Data Index: 666694 (C4 (Web Text))

Max Activating Token Index: 27

Text #4

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0688. Min Act: -0.0002

Data Index: 570479 (C4 (Web Text))

Max Activating Token Index: 549

Text #5

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0654. Min Act: -0.0002

Data Index: 120457 (C4 (Web Text))

Max Activating Token Index: 521

Text #6

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0603. Min Act: -0.0002

Data Index: 971530 (C4 (Web Text))

Max Activating Token Index: 505

Text #7

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0623. Min Act: -0.0003

Data Index: 666296 (C4 (Web Text))

Max Activating Token Index: 687

Text #8

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0608. Min Act: -0.0003

Data Index: 800297 (C4 (Web Text))

Max Activating Token Index: 844

Text #9

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0590. Min Act: -0.0003

Data Index: 90292 (C4 (Web Text))

Max Activating Token Index: 556

Text #10

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0599. Min Act: -0.0002

Data Index: 879580 (C4 (Web Text))

Max Activating Token Index: 820

Text #11

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0590. Min Act: -0.0002

Data Index: 7871 (C4 (Web Text))

Max Activating Token Index: 257

Text #12

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0591. Min Act: -0.0003

Data Index: 1155170 (C4 (Web Text))

Max Activating Token Index: 438

Text #13

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0593. Min Act: -0.0003

Data Index: 1325440 (C4 (Web Text))

Max Activating Token Index: 25

Text #14

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0585. Min Act: -0.0003

Data Index: 549812 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0573. Min Act: -0.0003

Data Index: 546269 (C4 (Web Text))

Max Activating Token Index: 602

Text #16

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0549. Min Act: -0.0002

Data Index: 766825 (C4 (Web Text))

Max Activating Token Index: 21

Text #17

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0537. Min Act: -0.0002

Data Index: 1329083 (C4 (Web Text))

Max Activating Token Index: 333

Text #18

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0530. Min Act: -0.0002

Data Index: 361294 (C4 (Web Text))

Max Activating Token Index: 706

Text #19

Max Range: 0.0831. Min Range: -0.0831

Max Act: 0.0542. Min Act: -0.0003

Data Index: 762937 (C4 (Web Text))

Max Activating Token Index: 623