Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3358 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1694. Min Act: -0.0000

Data Index: 1659390 (The Pile)

Max Activating Token Index: 334

Text #1

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1472. Min Act: -0.0000

Data Index: 490282 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1105. Min Act: -0.0000

Data Index: 831615 (The Pile)

Max Activating Token Index: 632

Text #3

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1062. Min Act: -0.0000

Data Index: 96480 (The Pile)

Max Activating Token Index: 511

Text #4

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0987. Min Act: -0.0000

Data Index: 219389 (The Pile)

Max Activating Token Index: 923

Text #5

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1007. Min Act: -0.0000

Data Index: 3786 (The Pile)

Max Activating Token Index: 920

Text #6

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.1037. Min Act: -0.0000

Data Index: 1847125 (The Pile)

Max Activating Token Index: 187

Text #7

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0857. Min Act: -0.0000

Data Index: 1849018 (The Pile)

Max Activating Token Index: 699

Text #8

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0953. Min Act: -0.0000

Data Index: 1466277 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0850. Min Act: -0.0000

Data Index: 1725978 (The Pile)

Max Activating Token Index: 372

Text #10

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0896. Min Act: -0.0000

Data Index: 534868 (The Pile)

Max Activating Token Index: 623

Text #11

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0898. Min Act: -0.0000

Data Index: 107632 (The Pile)

Max Activating Token Index: 517

Text #12

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0759. Min Act: -0.0000

Data Index: 1166030 (The Pile)

Max Activating Token Index: 1000

Text #13

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0824. Min Act: -0.0000

Data Index: 897771 (The Pile)

Max Activating Token Index: 769

Text #14

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1977999 (The Pile)

Max Activating Token Index: 576

Text #15

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0894. Min Act: -0.0000

Data Index: 1157348 (The Pile)

Max Activating Token Index: 774

Text #16

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0844. Min Act: -0.0000

Data Index: 300620 (The Pile)

Max Activating Token Index: 962

Text #17

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0757. Min Act: -0.0000

Data Index: 1632620 (The Pile)

Max Activating Token Index: 518

Text #18

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0722. Min Act: -0.0000

Data Index: 1655952 (The Pile)

Max Activating Token Index: 857

Text #19

Max Range: 0.1694. Min Range: -0.1694

Max Act: 0.0721. Min Act: -0.0000

Data Index: 1381159 (The Pile)

Max Activating Token Index: 808