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

Dataset: The Pile

Neuron 1040 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0000

Data Index: 1157980 (The Pile)

Max Activating Token Index: 2

Text #1

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0896. Min Act: -0.0000

Data Index: 522972 (The Pile)

Max Activating Token Index: 2

Text #2

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0886. Min Act: -0.0000

Data Index: 1975330 (The Pile)

Max Activating Token Index: 2

Text #3

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0872. Min Act: -0.0000

Data Index: 190513 (The Pile)

Max Activating Token Index: 18

Text #4

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0871. Min Act: -0.0001

Data Index: 567979 (The Pile)

Max Activating Token Index: 2

Text #5

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0871. Min Act: -0.0000

Data Index: 1091212 (The Pile)

Max Activating Token Index: 2

Text #6

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0893. Min Act: -0.0000

Data Index: 1279325 (The Pile)

Max Activating Token Index: 18

Text #7

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0862. Min Act: -0.0000

Data Index: 1368721 (The Pile)

Max Activating Token Index: 17

Text #8

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0856. Min Act: 0.0000

Data Index: 1084522 (The Pile)

Max Activating Token Index: 11

Text #9

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0857. Min Act: -0.0000

Data Index: 368610 (The Pile)

Max Activating Token Index: 3

Text #10

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0848. Min Act: -0.0000

Data Index: 994062 (The Pile)

Max Activating Token Index: 14

Text #11

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0845. Min Act: -0.0000

Data Index: 1621563 (The Pile)

Max Activating Token Index: 14

Text #12

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0841. Min Act: -0.0001

Data Index: 699464 (The Pile)

Max Activating Token Index: 21

Text #13

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0869. Min Act: -0.0000

Data Index: 1848484 (The Pile)

Max Activating Token Index: 8

Text #14

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0839. Min Act: 0.0000

Data Index: 489452 (The Pile)

Max Activating Token Index: 24

Text #15

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0838. Min Act: 0.0000

Data Index: 671606 (The Pile)

Max Activating Token Index: 10

Text #16

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0838. Min Act: 0.0000

Data Index: 158615 (The Pile)

Max Activating Token Index: 14

Text #17

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0833. Min Act: -0.0000

Data Index: 945791 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0831. Min Act: -0.0000

Data Index: 1453905 (The Pile)

Max Activating Token Index: 15

Text #19

Max Range: 0.0896. Min Range: -0.0896

Max Act: 0.0826. Min Act: -0.0000

Data Index: 1476543 (The Pile)

Max Activating Token Index: 42