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

Dataset: The Pile

Neuron 4772 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0623. Min Range: -1.0623

Max Act: 1.0623. Min Act: -0.0000

Data Index: 1930827 (The Pile)

Max Activating Token Index: 66

Text #1

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6273. Min Act: -0.0000

Data Index: 336335 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.6247. Min Act: -0.0000

Data Index: 1071066 (The Pile)

Max Activating Token Index: 61

Text #3

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.5650. Min Act: -0.0000

Data Index: 15873 (The Pile)

Max Activating Token Index: 1001

Text #4

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.5472. Min Act: -0.0000

Data Index: 440158 (The Pile)

Max Activating Token Index: 334

Text #5

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.5912. Min Act: -0.0000

Data Index: 417433 (The Pile)

Max Activating Token Index: 418

Text #6

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.5258. Min Act: -0.0000

Data Index: 92380 (The Pile)

Max Activating Token Index: 150

Text #7

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.5376. Min Act: -0.0000

Data Index: 139979 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4805. Min Act: -0.0000

Data Index: 1262538 (The Pile)

Max Activating Token Index: 790

Text #9

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4311. Min Act: -0.0000

Data Index: 368702 (The Pile)

Max Activating Token Index: 339

Text #10

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.5074. Min Act: -0.0000

Data Index: 765027 (The Pile)

Max Activating Token Index: 936

Text #11

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4708. Min Act: -0.0000

Data Index: 539893 (The Pile)

Max Activating Token Index: 227

Text #12

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4839. Min Act: -0.0000

Data Index: 1572629 (The Pile)

Max Activating Token Index: 207

Text #13

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4605. Min Act: -0.0000

Data Index: 1622632 (The Pile)

Max Activating Token Index: 179

Text #14

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4818. Min Act: -0.0000

Data Index: 787515 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4332. Min Act: -0.0000

Data Index: 280940 (The Pile)

Max Activating Token Index: 627

Text #16

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4583. Min Act: -0.0000

Data Index: 1196116 (The Pile)

Max Activating Token Index: 389

Text #17

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4355. Min Act: -0.0000

Data Index: 159495 (The Pile)

Max Activating Token Index: 82

Text #18

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4635. Min Act: -0.0000

Data Index: 1300638 (The Pile)

Max Activating Token Index: 200

Text #19

Max Range: 1.0623. Min Range: -1.0623

Max Act: 0.4428. Min Act: -0.0000

Data Index: 1764412 (The Pile)

Max Activating Token Index: 480