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

Dataset: The Pile

Neuron 2336 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: 1.1498. Min Range: -1.1498

Max Act: 1.1498. Min Act: -0.0000

Data Index: 234738 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1905983 (The Pile)

Max Activating Token Index: 668

Text #2

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0583. Min Act: -0.0000

Data Index: 60088 (The Pile)

Max Activating Token Index: 722

Text #3

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0122. Min Act: -0.0000

Data Index: 1895487 (The Pile)

Max Activating Token Index: 742

Text #4

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9801. Min Act: -0.0000

Data Index: 827544 (The Pile)

Max Activating Token Index: 737

Text #5

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9893. Min Act: -0.0000

Data Index: 1237892 (The Pile)

Max Activating Token Index: 691

Text #6

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9850. Min Act: -0.0000

Data Index: 1264150 (The Pile)

Max Activating Token Index: 173

Text #7

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9318. Min Act: -0.0000

Data Index: 788777 (The Pile)

Max Activating Token Index: 593

Text #8

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9509. Min Act: -0.0000

Data Index: 1461897 (The Pile)

Max Activating Token Index: 163

Text #9

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9589. Min Act: -0.0000

Data Index: 290041 (The Pile)

Max Activating Token Index: 301

Text #10

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9236. Min Act: -0.0000

Data Index: 350646 (The Pile)

Max Activating Token Index: 937

Text #11

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9254. Min Act: -0.0000

Data Index: 1936066 (The Pile)

Max Activating Token Index: 447

Text #12

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9408. Min Act: -0.0000

Data Index: 1077489 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9788. Min Act: -0.0000

Data Index: 191773 (The Pile)

Max Activating Token Index: 820

Text #14

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9416. Min Act: -0.0000

Data Index: 1411646 (The Pile)

Max Activating Token Index: 579

Text #15

Max Range: 1.1498. Min Range: -1.1498

Max Act: 1.0270. Min Act: -0.0000

Data Index: 1845535 (The Pile)

Max Activating Token Index: 548

Text #16

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8831. Min Act: -0.0000

Data Index: 1933049 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.9082. Min Act: -0.0000

Data Index: 1702820 (The Pile)

Max Activating Token Index: 850

Text #18

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1714986 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.1498. Min Range: -1.1498

Max Act: 0.8949. Min Act: -0.0000

Data Index: 891727 (The Pile)

Max Activating Token Index: 695