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

Dataset: The Pile

Neuron 162 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: 1.5751. Min Range: -1.5751

Max Act: 1.5751. Min Act: -0.0000

Data Index: 1636011 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.1601. Min Act: -0.0000

Data Index: 638790 (The Pile)

Max Activating Token Index: 691

Text #2

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.3411. Min Act: -0.0000

Data Index: 1099555 (The Pile)

Max Activating Token Index: 571

Text #3

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.1743. Min Act: -0.0000

Data Index: 4391 (The Pile)

Max Activating Token Index: 922

Text #4

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.3816. Min Act: -0.0000

Data Index: 402897 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.1740. Min Act: -0.0000

Data Index: 1093180 (The Pile)

Max Activating Token Index: 838

Text #6

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2746. Min Act: -0.0000

Data Index: 352551 (The Pile)

Max Activating Token Index: 596

Text #7

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.1273. Min Act: -0.0000

Data Index: 920532 (The Pile)

Max Activating Token Index: 810

Text #8

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.2410. Min Act: -0.0000

Data Index: 1063592 (The Pile)

Max Activating Token Index: 1009

Text #9

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.0176. Min Act: -0.0000

Data Index: 1004635 (The Pile)

Max Activating Token Index: 858

Text #10

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.0752. Min Act: -0.0000

Data Index: 72185 (The Pile)

Max Activating Token Index: 551

Text #11

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1268750 (The Pile)

Max Activating Token Index: 238

Text #12

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.9991. Min Act: -0.0000

Data Index: 406605 (The Pile)

Max Activating Token Index: 684

Text #13

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.0065. Min Act: -0.0000

Data Index: 1368540 (The Pile)

Max Activating Token Index: 810

Text #14

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.9108. Min Act: -0.0000

Data Index: 1404242 (The Pile)

Max Activating Token Index: 513

Text #15

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.9908. Min Act: -0.0000

Data Index: 1634421 (The Pile)

Max Activating Token Index: 569

Text #16

Max Range: 1.5751. Min Range: -1.5751

Max Act: 1.0102. Min Act: -0.0000

Data Index: 630060 (The Pile)

Max Activating Token Index: 1004

Text #17

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.9840. Min Act: -0.0000

Data Index: 53667 (The Pile)

Max Activating Token Index: 791

Text #18

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.9655. Min Act: -0.0000

Data Index: 1203498 (The Pile)

Max Activating Token Index: 810

Text #19

Max Range: 1.5751. Min Range: -1.5751

Max Act: 0.8859. Min Act: -0.0000

Data Index: 959155 (The Pile)

Max Activating Token Index: 974