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

Dataset: The Pile

Neuron 3856 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: 1.0637. Min Range: -1.0637

Max Act: 1.0637. Min Act: -0.0000

Data Index: 1249444 (The Pile)

Max Activating Token Index: 84

Text #1

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9832. Min Act: -0.0000

Data Index: 1222926 (The Pile)

Max Activating Token Index: 847

Text #2

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9209. Min Act: -0.0000

Data Index: 1920014 (The Pile)

Max Activating Token Index: 1020

Text #3

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7443. Min Act: -0.0000

Data Index: 1689655 (The Pile)

Max Activating Token Index: 779

Text #4

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9104. Min Act: -0.0000

Data Index: 1937112 (The Pile)

Max Activating Token Index: 78

Text #5

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9510. Min Act: -0.0000

Data Index: 435611 (The Pile)

Max Activating Token Index: 283

Text #6

Max Range: 1.0637. Min Range: -1.0637

Max Act: 1.0030. Min Act: -0.0000

Data Index: 1560731 (The Pile)

Max Activating Token Index: 741

Text #7

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9590. Min Act: -0.0000

Data Index: 1168864 (The Pile)

Max Activating Token Index: 622

Text #8

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9425. Min Act: -0.0000

Data Index: 650632 (The Pile)

Max Activating Token Index: 355

Text #9

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9092. Min Act: -0.0000

Data Index: 758979 (The Pile)

Max Activating Token Index: 644

Text #10

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.9826. Min Act: -0.0000

Data Index: 1535642 (The Pile)

Max Activating Token Index: 603

Text #11

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8432. Min Act: 0.0000

Data Index: 1332390 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1762658 (The Pile)

Max Activating Token Index: 430

Text #13

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8007. Min Act: -0.0000

Data Index: 120993 (The Pile)

Max Activating Token Index: 635

Text #14

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8352. Min Act: -0.0000

Data Index: 142927 (The Pile)

Max Activating Token Index: 893

Text #15

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8184. Min Act: -0.0000

Data Index: 1361525 (The Pile)

Max Activating Token Index: 411

Text #16

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8031. Min Act: 0.0000

Data Index: 305618 (The Pile)

Max Activating Token Index: 974

Text #17

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8222. Min Act: -0.0000

Data Index: 1872375 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.7922. Min Act: -0.0000

Data Index: 1418704 (The Pile)

Max Activating Token Index: 631

Text #19

Max Range: 1.0637. Min Range: -1.0637

Max Act: 0.8260. Min Act: -0.0000

Data Index: 1964569 (The Pile)

Max Activating Token Index: 71