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

Dataset: The Pile

Neuron 911 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: 0.0038. Min Range: -0.0038

Max Act: 0.0038. Min Act: -0.0000

Data Index: 613038 (The Pile)

Max Activating Token Index: 940

Text #1

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0035. Min Act: -0.0000

Data Index: 306840 (The Pile)

Max Activating Token Index: 890

Text #2

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0027. Min Act: -0.0000

Data Index: 1783779 (The Pile)

Max Activating Token Index: 746

Text #3

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0025. Min Act: -0.0000

Data Index: 645534 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0029. Min Act: -0.0000

Data Index: 1083934 (The Pile)

Max Activating Token Index: 685

Text #5

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0020. Min Act: -0.0000

Data Index: 52989 (The Pile)

Max Activating Token Index: 237

Text #6

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0018. Min Act: -0.0000

Data Index: 1490913 (The Pile)

Max Activating Token Index: 985

Text #7

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1182033 (The Pile)

Max Activating Token Index: 354

Text #8

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0015. Min Act: -0.0000

Data Index: 1373364 (The Pile)

Max Activating Token Index: 805

Text #9

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0013. Min Act: -0.0000

Data Index: 550732 (The Pile)

Max Activating Token Index: 759

Text #10

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0015. Min Act: -0.0000

Data Index: 675648 (The Pile)

Max Activating Token Index: 654

Text #11

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0014. Min Act: -0.0000

Data Index: 1402540 (The Pile)

Max Activating Token Index: 579

Text #12

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0010. Min Act: -0.0000

Data Index: 1116097 (The Pile)

Max Activating Token Index: 516

Text #13

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0010. Min Act: -0.0000

Data Index: 579995 (The Pile)

Max Activating Token Index: 563

Text #14

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0013. Min Act: -0.0000

Data Index: 350315 (The Pile)

Max Activating Token Index: 754

Text #15

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0012. Min Act: -0.0000

Data Index: 1599017 (The Pile)

Max Activating Token Index: 967

Text #16

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0009. Min Act: -0.0000

Data Index: 185514 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0012. Min Act: -0.0000

Data Index: 877639 (The Pile)

Max Activating Token Index: 858

Text #18

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0013. Min Act: -0.0000

Data Index: 1066926 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.0038. Min Range: -0.0038

Max Act: 0.0011. Min Act: -0.0000

Data Index: 1581047 (The Pile)

Max Activating Token Index: 911