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

Dataset: The Pile

Neuron 4446 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: 3.1991. Min Range: -3.1991

Max Act: 3.1991. Min Act: -0.0000

Data Index: 354154 (The Pile)

Max Activating Token Index: 431

Text #1

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.8912. Min Act: -0.0000

Data Index: 1039680 (The Pile)

Max Activating Token Index: 584

Text #2

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.9890. Min Act: -0.0000

Data Index: 100769 (The Pile)

Max Activating Token Index: 506

Text #3

Max Range: 3.1991. Min Range: -3.1991

Max Act: 3.0611. Min Act: -0.0000

Data Index: 1983078 (The Pile)

Max Activating Token Index: 950

Text #4

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.6729. Min Act: -0.0000

Data Index: 134087 (The Pile)

Max Activating Token Index: 823

Text #5

Max Range: 3.1991. Min Range: -3.1991

Max Act: 3.0119. Min Act: -0.0000

Data Index: 1873949 (The Pile)

Max Activating Token Index: 822

Text #6

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.8490. Min Act: -0.0000

Data Index: 1834531 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.8412. Min Act: -0.0000

Data Index: 290681 (The Pile)

Max Activating Token Index: 66

Text #8

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.6671. Min Act: -0.0000

Data Index: 1020302 (The Pile)

Max Activating Token Index: 397

Text #9

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.9097. Min Act: -0.0000

Data Index: 142858 (The Pile)

Max Activating Token Index: 210

Text #10

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.7688. Min Act: -0.0000

Data Index: 480732 (The Pile)

Max Activating Token Index: 496

Text #11

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.7243. Min Act: -0.0000

Data Index: 1556804 (The Pile)

Max Activating Token Index: 717

Text #12

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.7015. Min Act: -0.0000

Data Index: 1636603 (The Pile)

Max Activating Token Index: 743

Text #13

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.6497. Min Act: -0.0000

Data Index: 1177963 (The Pile)

Max Activating Token Index: 872

Text #14

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.6531. Min Act: -0.0000

Data Index: 1240443 (The Pile)

Max Activating Token Index: 613

Text #15

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.6296. Min Act: -0.0000

Data Index: 728282 (The Pile)

Max Activating Token Index: 83

Text #16

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.5305. Min Act: -0.0000

Data Index: 397433 (The Pile)

Max Activating Token Index: 226

Text #17

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.4019. Min Act: -0.0000

Data Index: 207475 (The Pile)

Max Activating Token Index: 456

Text #18

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.6150. Min Act: -0.0000

Data Index: 1419526 (The Pile)

Max Activating Token Index: 974

Text #19

Max Range: 3.1991. Min Range: -3.1991

Max Act: 2.7380. Min Act: -0.0000

Data Index: 30996 (The Pile)

Max Activating Token Index: 163