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

Dataset: The Pile

Neuron 3104 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: 1.2824. Min Range: -1.2824

Max Act: 1.2824. Min Act: -0.0000

Data Index: 828731 (The Pile)

Max Activating Token Index: 219

Text #1

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.1309. Min Act: -0.0000

Data Index: 532981 (The Pile)

Max Activating Token Index: 336

Text #2

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0736. Min Act: -0.0000

Data Index: 80589 (The Pile)

Max Activating Token Index: 595

Text #3

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9471. Min Act: -0.0000

Data Index: 955041 (The Pile)

Max Activating Token Index: 828

Text #4

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9805. Min Act: -0.0000

Data Index: 738599 (The Pile)

Max Activating Token Index: 97

Text #5

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9477. Min Act: -0.0000

Data Index: 1323147 (The Pile)

Max Activating Token Index: 875

Text #6

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0010. Min Act: -0.0000

Data Index: 607030 (The Pile)

Max Activating Token Index: 661

Text #7

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9028. Min Act: -0.0000

Data Index: 146206 (The Pile)

Max Activating Token Index: 1023

Text #8

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9945. Min Act: -0.0000

Data Index: 125209 (The Pile)

Max Activating Token Index: 641

Text #9

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9309. Min Act: -0.0000

Data Index: 725275 (The Pile)

Max Activating Token Index: 604

Text #10

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9342. Min Act: -0.0000

Data Index: 1078455 (The Pile)

Max Activating Token Index: 768

Text #11

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9194. Min Act: -0.0000

Data Index: 1615933 (The Pile)

Max Activating Token Index: 110

Text #12

Max Range: 1.2824. Min Range: -1.2824

Max Act: 1.0293. Min Act: -0.0000

Data Index: 110913 (The Pile)

Max Activating Token Index: 845

Text #13

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9410. Min Act: -0.0000

Data Index: 1424794 (The Pile)

Max Activating Token Index: 1019

Text #14

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9312. Min Act: -0.0000

Data Index: 416663 (The Pile)

Max Activating Token Index: 975

Text #15

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9294. Min Act: -0.0000

Data Index: 474555 (The Pile)

Max Activating Token Index: 806

Text #16

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9013. Min Act: -0.0000

Data Index: 518945 (The Pile)

Max Activating Token Index: 775

Text #17

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9187. Min Act: -0.0000

Data Index: 608984 (The Pile)

Max Activating Token Index: 1009

Text #18

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9078. Min Act: -0.0000

Data Index: 1815010 (The Pile)

Max Activating Token Index: 95

Text #19

Max Range: 1.2824. Min Range: -1.2824

Max Act: 0.9002. Min Act: -0.0000

Data Index: 532594 (The Pile)

Max Activating Token Index: 827