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

Dataset: The Pile

Neuron 3312 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: 0.0101. Min Range: -0.0101

Max Act: 0.0101. Min Act: -0.0000

Data Index: 1601739 (The Pile)

Max Activating Token Index: 758

Text #1

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0032. Min Act: -0.0000

Data Index: 340493 (The Pile)

Max Activating Token Index: 382

Text #2

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0022. Min Act: -0.0000

Data Index: 1683649 (The Pile)

Max Activating Token Index: 991

Text #3

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0020. Min Act: -0.0000

Data Index: 1036299 (The Pile)

Max Activating Token Index: 890

Text #4

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0019. Min Act: -0.0000

Data Index: 1262550 (The Pile)

Max Activating Token Index: 777

Text #5

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0020. Min Act: -0.0000

Data Index: 748720 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0020. Min Act: -0.0000

Data Index: 247342 (The Pile)

Max Activating Token Index: 939

Text #7

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0018. Min Act: -0.0000

Data Index: 677654 (The Pile)

Max Activating Token Index: 264

Text #8

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1294051 (The Pile)

Max Activating Token Index: 918

Text #9

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0017. Min Act: -0.0000

Data Index: 392670 (The Pile)

Max Activating Token Index: 742

Text #10

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0019. Min Act: -0.0000

Data Index: 640196 (The Pile)

Max Activating Token Index: 851

Text #11

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1490913 (The Pile)

Max Activating Token Index: 985

Text #12

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0016. Min Act: -0.0000

Data Index: 1204064 (The Pile)

Max Activating Token Index: 452

Text #13

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1587129 (The Pile)

Max Activating Token Index: 609

Text #14

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1572251 (The Pile)

Max Activating Token Index: 797

Text #15

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1272574 (The Pile)

Max Activating Token Index: 755

Text #16

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1529157 (The Pile)

Max Activating Token Index: 621

Text #17

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0015. Min Act: -0.0000

Data Index: 173718 (The Pile)

Max Activating Token Index: 675

Text #18

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1869710 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 0.0101. Min Range: -0.0101

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1075884 (The Pile)

Max Activating Token Index: 592