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

Dataset: The Pile

Neuron 4756 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: 0.1285. Min Range: -0.1285

Max Act: 0.1285. Min Act: -0.0000

Data Index: 1942123 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1117. Min Act: -0.0000

Data Index: 1102370 (The Pile)

Max Activating Token Index: 948

Text #2

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0984. Min Act: -0.0000

Data Index: 1238504 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.1017. Min Act: -0.0000

Data Index: 1951722 (The Pile)

Max Activating Token Index: 24

Text #4

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0985. Min Act: -0.0000

Data Index: 930185 (The Pile)

Max Activating Token Index: 299

Text #5

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0814. Min Act: -0.0000

Data Index: 1772054 (The Pile)

Max Activating Token Index: 55

Text #6

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0944. Min Act: -0.0000

Data Index: 703412 (The Pile)

Max Activating Token Index: 959

Text #7

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0898. Min Act: -0.0000

Data Index: 1326729 (The Pile)

Max Activating Token Index: 50

Text #8

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0943. Min Act: -0.0000

Data Index: 703416 (The Pile)

Max Activating Token Index: 109

Text #9

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0908. Min Act: -0.0000

Data Index: 61930 (The Pile)

Max Activating Token Index: 25

Text #10

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0910. Min Act: -0.0000

Data Index: 1560302 (The Pile)

Max Activating Token Index: 391

Text #11

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0868. Min Act: -0.0000

Data Index: 1870279 (The Pile)

Max Activating Token Index: 106

Text #12

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0887. Min Act: -0.0000

Data Index: 1275259 (The Pile)

Max Activating Token Index: 211

Text #13

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0853. Min Act: -0.0000

Data Index: 938650 (The Pile)

Max Activating Token Index: 102

Text #14

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0882. Min Act: 0.0000

Data Index: 1627591 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1005735 (The Pile)

Max Activating Token Index: 38

Text #16

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0837. Min Act: -0.0000

Data Index: 492213 (The Pile)

Max Activating Token Index: 108

Text #17

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0864. Min Act: -0.0000

Data Index: 444063 (The Pile)

Max Activating Token Index: 990

Text #18

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0888. Min Act: -0.0000

Data Index: 124037 (The Pile)

Max Activating Token Index: 68

Text #19

Max Range: 0.1285. Min Range: -0.1285

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1099987 (The Pile)

Max Activating Token Index: 419