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

Dataset: The Pile

Neuron 4455 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1379. Min Act: -0.0000

Data Index: 464720 (The Pile)

Max Activating Token Index: 300

Text #1

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1086. Min Act: -0.0000

Data Index: 1205269 (The Pile)

Max Activating Token Index: 775

Text #2

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1052. Min Act: -0.0000

Data Index: 460592 (The Pile)

Max Activating Token Index: 592

Text #3

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1462525 (The Pile)

Max Activating Token Index: 765

Text #4

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0982. Min Act: -0.0000

Data Index: 1350624 (The Pile)

Max Activating Token Index: 633

Text #5

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0891. Min Act: -0.0000

Data Index: 1063688 (The Pile)

Max Activating Token Index: 880

Text #6

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0976. Min Act: -0.0000

Data Index: 1672486 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0876. Min Act: -0.0000

Data Index: 75855 (The Pile)

Max Activating Token Index: 531

Text #8

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0849. Min Act: -0.0000

Data Index: 708842 (The Pile)

Max Activating Token Index: 825

Text #9

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0786. Min Act: -0.0000

Data Index: 683730 (The Pile)

Max Activating Token Index: 596

Text #10

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0893. Min Act: -0.0000

Data Index: 316649 (The Pile)

Max Activating Token Index: 540

Text #11

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0894. Min Act: -0.0000

Data Index: 728149 (The Pile)

Max Activating Token Index: 381

Text #12

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0798. Min Act: -0.0000

Data Index: 928614 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0923. Min Act: -0.0000

Data Index: 556873 (The Pile)

Max Activating Token Index: 572

Text #14

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1929723 (The Pile)

Max Activating Token Index: 362

Text #15

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1851631 (The Pile)

Max Activating Token Index: 641

Text #16

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0843. Min Act: -0.0000

Data Index: 1195781 (The Pile)

Max Activating Token Index: 668

Text #17

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0814. Min Act: -0.0000

Data Index: 693854 (The Pile)

Max Activating Token Index: 409

Text #18

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0886. Min Act: -0.0000

Data Index: 840516 (The Pile)

Max Activating Token Index: 432

Text #19

Max Range: 0.1379. Min Range: -0.1379

Max Act: 0.0818. Min Act: -0.0000

Data Index: 232266 (The Pile)

Max Activating Token Index: 1022