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

Dataset: The Pile

Neuron 3614 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.3847. Min Act: -0.0000

Data Index: 602283 (The Pile)

Max Activating Token Index: 582

Text #1

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.3999. Min Act: -0.0000

Data Index: 1168303 (The Pile)

Max Activating Token Index: 316

Text #2

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1653425 (The Pile)

Max Activating Token Index: 46

Text #3

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.5077. Min Act: -0.0000

Data Index: 130875 (The Pile)

Max Activating Token Index: 91

Text #4

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2707. Min Act: -0.0000

Data Index: 1614777 (The Pile)

Max Activating Token Index: 395

Text #5

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2755. Min Act: -0.0000

Data Index: 829864 (The Pile)

Max Activating Token Index: 654

Text #6

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2964. Min Act: -0.0000

Data Index: 1849356 (The Pile)

Max Activating Token Index: 119

Text #7

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.3317. Min Act: -0.0000

Data Index: 911812 (The Pile)

Max Activating Token Index: 775

Text #8

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2730. Min Act: -0.0000

Data Index: 1230347 (The Pile)

Max Activating Token Index: 184

Text #9

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.3249. Min Act: -0.0000

Data Index: 808363 (The Pile)

Max Activating Token Index: 231

Text #10

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.3117. Min Act: -0.0000

Data Index: 256323 (The Pile)

Max Activating Token Index: 826

Text #11

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2773. Min Act: -0.0000

Data Index: 493165 (The Pile)

Max Activating Token Index: 536

Text #12

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2220. Min Act: -0.0000

Data Index: 865509 (The Pile)

Max Activating Token Index: 110

Text #13

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.1726. Min Act: -0.0000

Data Index: 533087 (The Pile)

Max Activating Token Index: 904

Text #14

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1349625 (The Pile)

Max Activating Token Index: 824

Text #15

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.1888. Min Act: -0.0000

Data Index: 837720 (The Pile)

Max Activating Token Index: 73

Text #16

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.1628. Min Act: -0.0000

Data Index: 214102 (The Pile)

Max Activating Token Index: 588

Text #17

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.1802. Min Act: -0.0000

Data Index: 915199 (The Pile)

Max Activating Token Index: 786

Text #18

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.1772. Min Act: -0.0000

Data Index: 1366723 (The Pile)

Max Activating Token Index: 841

Text #19

Max Range: 1.5077. Min Range: -1.5077

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1363973 (The Pile)

Max Activating Token Index: 1014