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

Dataset: The Pile

Neuron 3473 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.5049. Min Act: -0.0000

Data Index: 1899503 (The Pile)

Max Activating Token Index: 314

Text #1

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.4899. Min Act: -0.0000

Data Index: 1905758 (The Pile)

Max Activating Token Index: 846

Text #2

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3614. Min Act: -0.0000

Data Index: 1949573 (The Pile)

Max Activating Token Index: 1010

Text #3

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3337. Min Act: -0.0000

Data Index: 397939 (The Pile)

Max Activating Token Index: 475

Text #4

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.3564. Min Act: -0.0000

Data Index: 505653 (The Pile)

Max Activating Token Index: 656

Text #5

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2525. Min Act: -0.0000

Data Index: 1611575 (The Pile)

Max Activating Token Index: 1017

Text #6

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2866. Min Act: -0.0000

Data Index: 111475 (The Pile)

Max Activating Token Index: 335

Text #7

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2011. Min Act: -0.0000

Data Index: 286106 (The Pile)

Max Activating Token Index: 508

Text #8

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2445. Min Act: -0.0000

Data Index: 132923 (The Pile)

Max Activating Token Index: 540

Text #9

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2215. Min Act: -0.0000

Data Index: 963849 (The Pile)

Max Activating Token Index: 1004

Text #10

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.2251. Min Act: -0.0000

Data Index: 270163 (The Pile)

Max Activating Token Index: 34

Text #11

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1090. Min Act: -0.0000

Data Index: 949691 (The Pile)

Max Activating Token Index: 918

Text #12

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0931. Min Act: -0.0000

Data Index: 1978808 (The Pile)

Max Activating Token Index: 349

Text #13

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1610. Min Act: -0.0000

Data Index: 533930 (The Pile)

Max Activating Token Index: 755

Text #14

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1785575 (The Pile)

Max Activating Token Index: 895

Text #15

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1507. Min Act: -0.0000

Data Index: 1972885 (The Pile)

Max Activating Token Index: 326

Text #16

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.1389. Min Act: -0.0000

Data Index: 1488341 (The Pile)

Max Activating Token Index: 894

Text #17

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0193. Min Act: -0.0000

Data Index: 1623974 (The Pile)

Max Activating Token Index: 880

Text #18

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0855. Min Act: -0.0000

Data Index: 1521441 (The Pile)

Max Activating Token Index: 893

Text #19

Max Range: 1.5049. Min Range: -1.5049

Max Act: 1.0696. Min Act: -0.0000

Data Index: 123755 (The Pile)

Max Activating Token Index: 169