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

Dataset: The Pile

Neuron 4679 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: 0.1472. Min Range: -0.1472

Max Act: 0.1411. Min Act: -0.0000

Data Index: 904746 (The Pile)

Max Activating Token Index: 161

Text #1

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1472. Min Act: -0.0000

Data Index: 567776 (The Pile)

Max Activating Token Index: 136

Text #2

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0997. Min Act: -0.0000

Data Index: 1086663 (The Pile)

Max Activating Token Index: 278

Text #3

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.1125. Min Act: -0.0000

Data Index: 1404045 (The Pile)

Max Activating Token Index: 403

Text #4

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0983. Min Act: -0.0000

Data Index: 1394384 (The Pile)

Max Activating Token Index: 995

Text #5

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0876. Min Act: -0.0000

Data Index: 1736660 (The Pile)

Max Activating Token Index: 884

Text #6

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0922. Min Act: -0.0000

Data Index: 1052340 (The Pile)

Max Activating Token Index: 267

Text #7

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0967. Min Act: -0.0000

Data Index: 1785157 (The Pile)

Max Activating Token Index: 941

Text #8

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0790. Min Act: -0.0000

Data Index: 1779390 (The Pile)

Max Activating Token Index: 732

Text #9

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0813. Min Act: -0.0000

Data Index: 368342 (The Pile)

Max Activating Token Index: 827

Text #10

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1949691 (The Pile)

Max Activating Token Index: 432

Text #11

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0788. Min Act: -0.0000

Data Index: 140393 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0859. Min Act: -0.0000

Data Index: 1509303 (The Pile)

Max Activating Token Index: 343

Text #13

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0875. Min Act: -0.0000

Data Index: 508730 (The Pile)

Max Activating Token Index: 292

Text #14

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0811. Min Act: -0.0000

Data Index: 416098 (The Pile)

Max Activating Token Index: 958

Text #15

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0905. Min Act: -0.0000

Data Index: 1213714 (The Pile)

Max Activating Token Index: 232

Text #16

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0795. Min Act: -0.0000

Data Index: 1174297 (The Pile)

Max Activating Token Index: 965

Text #17

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0903. Min Act: -0.0000

Data Index: 652370 (The Pile)

Max Activating Token Index: 709

Text #18

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0849. Min Act: -0.0000

Data Index: 1145635 (The Pile)

Max Activating Token Index: 361

Text #19

Max Range: 0.1472. Min Range: -0.1472

Max Act: 0.0828. Min Act: -0.0000

Data Index: 1262321 (The Pile)

Max Activating Token Index: 786