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

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

Neuron 734 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: 0.0844. Min Range: -0.0844

Max Act: 0.0844. Min Act: -0.0002

Data Index: 800555 (C4 (Web Text))

Max Activating Token Index: 8

Text #1

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0771. Min Act: -0.0003

Data Index: 883304 (C4 (Web Text))

Max Activating Token Index: 655

Text #2

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0742. Min Act: -0.0003

Data Index: 402730 (C4 (Web Text))

Max Activating Token Index: 914

Text #3

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0724. Min Act: -0.0004

Data Index: 146809 (C4 (Web Text))

Max Activating Token Index: 979

Text #4

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0663. Min Act: -0.0003

Data Index: 1216398 (C4 (Web Text))

Max Activating Token Index: 869

Text #5

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0661. Min Act: -0.0002

Data Index: 686430 (C4 (Web Text))

Max Activating Token Index: 314

Text #6

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0643. Min Act: -0.0003

Data Index: 328000 (C4 (Web Text))

Max Activating Token Index: 308

Text #7

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0647. Min Act: -0.0002

Data Index: 904902 (C4 (Web Text))

Max Activating Token Index: 361

Text #8

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0631. Min Act: -0.0001

Data Index: 97902 (C4 (Web Text))

Max Activating Token Index: 225

Text #9

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0627. Min Act: -0.0003

Data Index: 505209 (C4 (Web Text))

Max Activating Token Index: 285

Text #10

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0654. Min Act: -0.0002

Data Index: 388065 (C4 (Web Text))

Max Activating Token Index: 604

Text #11

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0630. Min Act: -0.0002

Data Index: 557183 (C4 (Web Text))

Max Activating Token Index: 373

Text #12

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0625. Min Act: -0.0003

Data Index: 461129 (C4 (Web Text))

Max Activating Token Index: 413

Text #13

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0631. Min Act: -0.0003

Data Index: 1080069 (C4 (Web Text))

Max Activating Token Index: 758

Text #14

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0605. Min Act: -0.0002

Data Index: 541854 (C4 (Web Text))

Max Activating Token Index: 56

Text #15

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0626. Min Act: -0.0003

Data Index: 409736 (C4 (Web Text))

Max Activating Token Index: 999

Text #16

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0588. Min Act: -0.0004

Data Index: 1349826 (C4 (Web Text))

Max Activating Token Index: 295

Text #17

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0592. Min Act: -0.0003

Data Index: 1257227 (C4 (Web Text))

Max Activating Token Index: 354

Text #18

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0614. Min Act: -0.0003

Data Index: 359121 (C4 (Web Text))

Max Activating Token Index: 13

Text #19

Max Range: 0.0844. Min Range: -0.0844

Max Act: 0.0581. Min Act: -0.0004

Data Index: 268581 (C4 (Web Text))

Max Activating Token Index: 615