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

Dataset: The Pile

Neuron 310 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.1038. Min Act: 0.0000

Data Index: 592015 (The Pile)

Max Activating Token Index: 9

Text #1

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0997. Min Act: 0.0001

Data Index: 1745863 (The Pile)

Max Activating Token Index: 185

Text #2

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0975. Min Act: -0.0000

Data Index: 1700884 (The Pile)

Max Activating Token Index: 27

Text #3

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0941. Min Act: -0.0000

Data Index: 1627154 (The Pile)

Max Activating Token Index: 310

Text #4

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0939. Min Act: 0.0001

Data Index: 726649 (The Pile)

Max Activating Token Index: 264

Text #5

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0909. Min Act: 0.0000

Data Index: 994031 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0879. Min Act: -0.0000

Data Index: 1439984 (The Pile)

Max Activating Token Index: 4

Text #7

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0879. Min Act: -0.0000

Data Index: 287177 (The Pile)

Max Activating Token Index: 31

Text #8

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0847. Min Act: -0.0000

Data Index: 1318135 (The Pile)

Max Activating Token Index: 39

Text #9

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0862. Min Act: -0.0000

Data Index: 845043 (The Pile)

Max Activating Token Index: 4

Text #10

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0825. Min Act: 0.0001

Data Index: 61718 (The Pile)

Max Activating Token Index: 43

Text #11

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0824. Min Act: 0.0000

Data Index: 104070 (The Pile)

Max Activating Token Index: 15

Text #12

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0848. Min Act: 0.0001

Data Index: 1173507 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0837. Min Act: 0.0000

Data Index: 1464166 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0833. Min Act: 0.0000

Data Index: 684906 (The Pile)

Max Activating Token Index: 33

Text #15

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0832. Min Act: -0.0000

Data Index: 1744910 (The Pile)

Max Activating Token Index: 245

Text #16

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0787. Min Act: 0.0000

Data Index: 878409 (The Pile)

Max Activating Token Index: 39

Text #17

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0814. Min Act: -0.0000

Data Index: 931934 (The Pile)

Max Activating Token Index: 746

Text #18

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0815. Min Act: 0.0000

Data Index: 1761070 (The Pile)

Max Activating Token Index: 65

Text #19

Max Range: 0.1038. Min Range: -0.1038

Max Act: 0.0813. Min Act: -0.0000

Data Index: 1271037 (The Pile)

Max Activating Token Index: 37