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

Dataset: The Pile

Neuron 958 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.8629. Min Act: -0.0000

Data Index: 1811909 (The Pile)

Max Activating Token Index: 858

Text #1

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7921. Min Act: -0.0000

Data Index: 1441486 (The Pile)

Max Activating Token Index: 695

Text #2

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7888. Min Act: -0.0000

Data Index: 256833 (The Pile)

Max Activating Token Index: 132

Text #3

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6711. Min Act: -0.0000

Data Index: 1598073 (The Pile)

Max Activating Token Index: 969

Text #4

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7775. Min Act: -0.0000

Data Index: 593357 (The Pile)

Max Activating Token Index: 968

Text #5

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.8013. Min Act: -0.0000

Data Index: 1512112 (The Pile)

Max Activating Token Index: 374

Text #6

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7732. Min Act: -0.0000

Data Index: 1050892 (The Pile)

Max Activating Token Index: 251

Text #7

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.8009. Min Act: -0.0000

Data Index: 565065 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7915. Min Act: -0.0000

Data Index: 986885 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7593. Min Act: -0.0000

Data Index: 1291909 (The Pile)

Max Activating Token Index: 873

Text #10

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7502. Min Act: 0.0000

Data Index: 1549760 (The Pile)

Max Activating Token Index: 189

Text #11

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7413. Min Act: -0.0000

Data Index: 1732745 (The Pile)

Max Activating Token Index: 937

Text #12

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7107. Min Act: -0.0000

Data Index: 143166 (The Pile)

Max Activating Token Index: 595

Text #13

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7247. Min Act: -0.0000

Data Index: 935969 (The Pile)

Max Activating Token Index: 171

Text #14

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7494. Min Act: -0.0000

Data Index: 748620 (The Pile)

Max Activating Token Index: 560

Text #15

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1034475 (The Pile)

Max Activating Token Index: 934

Text #16

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6720. Min Act: -0.0000

Data Index: 251778 (The Pile)

Max Activating Token Index: 982

Text #17

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.6905. Min Act: -0.0000

Data Index: 117928 (The Pile)

Max Activating Token Index: 486

Text #18

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.7150. Min Act: -0.0000

Data Index: 1762255 (The Pile)

Max Activating Token Index: 962

Text #19

Max Range: 0.8629. Min Range: -0.8629

Max Act: 0.5845. Min Act: -0.0000

Data Index: 209304 (The Pile)

Max Activating Token Index: 677