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

Dataset: The Pile

Neuron 3522 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.5352. Min Act: -0.0000

Data Index: 1044309 (The Pile)

Max Activating Token Index: 738

Text #1

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.3416. Min Act: 0.0000

Data Index: 1224260 (The Pile)

Max Activating Token Index: 842

Text #2

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2873. Min Act: -0.0000

Data Index: 131626 (The Pile)

Max Activating Token Index: 654

Text #3

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.1612. Min Act: -0.0000

Data Index: 243152 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.2085. Min Act: 0.0000

Data Index: 818838 (The Pile)

Max Activating Token Index: 105

Text #5

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.0983. Min Act: -0.0000

Data Index: 1986182 (The Pile)

Max Activating Token Index: 505

Text #6

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.0854. Min Act: -0.0000

Data Index: 1913815 (The Pile)

Max Activating Token Index: 85

Text #7

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9955. Min Act: -0.0000

Data Index: 1930402 (The Pile)

Max Activating Token Index: 854

Text #8

Max Range: 1.5352. Min Range: -1.5352

Max Act: 1.0232. Min Act: -0.0000

Data Index: 809643 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9218. Min Act: -0.0000

Data Index: 1677501 (The Pile)

Max Activating Token Index: 207

Text #10

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9354. Min Act: -0.0000

Data Index: 346280 (The Pile)

Max Activating Token Index: 802

Text #11

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9068. Min Act: -0.0000

Data Index: 936569 (The Pile)

Max Activating Token Index: 573

Text #12

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9714. Min Act: -0.0000

Data Index: 1917953 (The Pile)

Max Activating Token Index: 1021

Text #13

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9486. Min Act: -0.0000

Data Index: 1279230 (The Pile)

Max Activating Token Index: 255

Text #14

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.8781. Min Act: -0.0000

Data Index: 831517 (The Pile)

Max Activating Token Index: 162

Text #15

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.8732. Min Act: -0.0000

Data Index: 1656301 (The Pile)

Max Activating Token Index: 25

Text #16

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.8396. Min Act: -0.0000

Data Index: 428274 (The Pile)

Max Activating Token Index: 66

Text #17

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9974. Min Act: -0.0000

Data Index: 1698577 (The Pile)

Max Activating Token Index: 13

Text #18

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.9000. Min Act: -0.0000

Data Index: 1480573 (The Pile)

Max Activating Token Index: 134

Text #19

Max Range: 1.5352. Min Range: -1.5352

Max Act: 0.8549. Min Act: -0.0000

Data Index: 785861 (The Pile)

Max Activating Token Index: 78