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

Dataset: The Pile

Neuron 3491 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1165679 (The Pile)

Max Activating Token Index: 649

Text #1

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5250. Min Act: -0.0000

Data Index: 576663 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5554. Min Act: -0.0000

Data Index: 1343910 (The Pile)

Max Activating Token Index: 91

Text #3

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5131. Min Act: -0.0000

Data Index: 384638 (The Pile)

Max Activating Token Index: 442

Text #4

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.5096. Min Act: -0.0000

Data Index: 1030464 (The Pile)

Max Activating Token Index: 772

Text #5

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4850. Min Act: -0.0000

Data Index: 903263 (The Pile)

Max Activating Token Index: 489

Text #6

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4878. Min Act: -0.0000

Data Index: 1368339 (The Pile)

Max Activating Token Index: 428

Text #7

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4796. Min Act: -0.0000

Data Index: 1406209 (The Pile)

Max Activating Token Index: 118

Text #8

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4480. Min Act: -0.0000

Data Index: 1112108 (The Pile)

Max Activating Token Index: 910

Text #9

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4733. Min Act: -0.0000

Data Index: 1039033 (The Pile)

Max Activating Token Index: 51

Text #10

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4823. Min Act: -0.0000

Data Index: 1696055 (The Pile)

Max Activating Token Index: 256

Text #11

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4416. Min Act: -0.0000

Data Index: 1968762 (The Pile)

Max Activating Token Index: 256

Text #12

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4407. Min Act: -0.0000

Data Index: 1684881 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4379. Min Act: -0.0000

Data Index: 295072 (The Pile)

Max Activating Token Index: 315

Text #14

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4355. Min Act: -0.0000

Data Index: 1590316 (The Pile)

Max Activating Token Index: 615

Text #15

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4492. Min Act: -0.0000

Data Index: 1509770 (The Pile)

Max Activating Token Index: 59

Text #16

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4362. Min Act: -0.0000

Data Index: 368959 (The Pile)

Max Activating Token Index: 383

Text #17

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4374. Min Act: -0.0000

Data Index: 814634 (The Pile)

Max Activating Token Index: 621

Text #18

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4284. Min Act: -0.0000

Data Index: 854686 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 0.5813. Min Range: -0.5813

Max Act: 0.4400. Min Act: -0.0000

Data Index: 1644613 (The Pile)

Max Activating Token Index: 99