Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 2737 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1122. Min Range: -1.1122

Max Act: 1.1122. Min Act: -0.0000

Data Index: 310636 (The Pile)

Max Activating Token Index: 604

Text #1

Max Range: 1.1122. Min Range: -1.1122

Max Act: 1.0084. Min Act: -0.0000

Data Index: 929915 (The Pile)

Max Activating Token Index: 816

Text #2

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9578. Min Act: -0.0000

Data Index: 833774 (The Pile)

Max Activating Token Index: 890

Text #3

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8998. Min Act: -0.0000

Data Index: 994199 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 1.1122. Min Range: -1.1122

Max Act: 1.0116. Min Act: -0.0000

Data Index: 54695 (The Pile)

Max Activating Token Index: 739

Text #5

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9969. Min Act: -0.0000

Data Index: 227017 (The Pile)

Max Activating Token Index: 689

Text #6

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8690. Min Act: -0.0000

Data Index: 1043840 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9848. Min Act: -0.0000

Data Index: 231334 (The Pile)

Max Activating Token Index: 409

Text #8

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9131. Min Act: -0.0000

Data Index: 215048 (The Pile)

Max Activating Token Index: 882

Text #9

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8919. Min Act: -0.0000

Data Index: 45238 (The Pile)

Max Activating Token Index: 556

Text #10

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8271. Min Act: -0.0000

Data Index: 1900657 (The Pile)

Max Activating Token Index: 800

Text #11

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9537. Min Act: -0.0000

Data Index: 1083968 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9213. Min Act: 0.0000

Data Index: 1656023 (The Pile)

Max Activating Token Index: 356

Text #13

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9148. Min Act: 0.0000

Data Index: 887054 (The Pile)

Max Activating Token Index: 392

Text #14

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9230. Min Act: -0.0000

Data Index: 1180715 (The Pile)

Max Activating Token Index: 851

Text #15

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9439. Min Act: -0.0000

Data Index: 724457 (The Pile)

Max Activating Token Index: 890

Text #16

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9378. Min Act: -0.0000

Data Index: 1921360 (The Pile)

Max Activating Token Index: 247

Text #17

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8820. Min Act: -0.0000

Data Index: 1840768 (The Pile)

Max Activating Token Index: 912

Text #18

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1701982 (The Pile)

Max Activating Token Index: 953

Text #19

Max Range: 1.1122. Min Range: -1.1122

Max Act: 0.8823. Min Act: -0.0000

Data Index: 70603 (The Pile)

Max Activating Token Index: 809