Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

Dataset: The Pile

Neuron 1002 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l-pile')

Text #0

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0996. Min Act: -0.0004

Data Index: 1216750 (The Pile)

Max Activating Token Index: 778

Text #1

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0991. Min Act: -0.0004

Data Index: 1270433 (The Pile)

Max Activating Token Index: 694

Text #2

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0938. Min Act: -0.0004

Data Index: 826288 (The Pile)

Max Activating Token Index: 774

Text #3

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0925. Min Act: -0.0004

Data Index: 462543 (The Pile)

Max Activating Token Index: 733

Text #4

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0969. Min Act: -0.0004

Data Index: 507743 (The Pile)

Max Activating Token Index: 308

Text #5

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0942. Min Act: -0.0004

Data Index: 1551517 (The Pile)

Max Activating Token Index: 504

Text #6

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0866. Min Act: -0.0004

Data Index: 816916 (The Pile)

Max Activating Token Index: 684

Text #7

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0899. Min Act: -0.0004

Data Index: 985128 (The Pile)

Max Activating Token Index: 763

Text #8

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0882. Min Act: -0.0004

Data Index: 133210 (The Pile)

Max Activating Token Index: 298

Text #9

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0883. Min Act: -0.0004

Data Index: 1508759 (The Pile)

Max Activating Token Index: 1000

Text #10

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0885. Min Act: -0.0004

Data Index: 977882 (The Pile)

Max Activating Token Index: 232

Text #11

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0850. Min Act: -0.0004

Data Index: 254643 (The Pile)

Max Activating Token Index: 738

Text #12

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0895. Min Act: -0.0004

Data Index: 364227 (The Pile)

Max Activating Token Index: 733

Text #13

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0858. Min Act: -0.0004

Data Index: 1177701 (The Pile)

Max Activating Token Index: 844

Text #14

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0918. Min Act: -0.0004

Data Index: 1483738 (The Pile)

Max Activating Token Index: 450

Text #15

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0884. Min Act: -0.0004

Data Index: 429898 (The Pile)

Max Activating Token Index: 775

Text #16

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0866. Min Act: -0.0004

Data Index: 1517808 (The Pile)

Max Activating Token Index: 586

Text #17

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0849. Min Act: -0.0004

Data Index: 1848236 (The Pile)

Max Activating Token Index: 436

Text #18

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0860. Min Act: -0.0004

Data Index: 367001 (The Pile)

Max Activating Token Index: 496

Text #19

Max Range: 0.0996. Min Range: -0.0996

Max Act: 0.0823. Min Act: -0.0004

Data Index: 1063826 (The Pile)

Max Activating Token Index: 84