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

Dataset: The Pile

Neuron 2121 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0692. Min Act: -0.0000

Data Index: 1628527 (The Pile)

Max Activating Token Index: 65

Text #1

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0182. Min Act: -0.0000

Data Index: 1870765 (The Pile)

Max Activating Token Index: 776

Text #2

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0111. Min Act: -0.0000

Data Index: 614131 (The Pile)

Max Activating Token Index: 352

Text #3

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0051. Min Act: -0.0000

Data Index: 1248899 (The Pile)

Max Activating Token Index: 347

Text #4

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9814. Min Act: -0.0000

Data Index: 668041 (The Pile)

Max Activating Token Index: 327

Text #5

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.9787. Min Act: -0.0000

Data Index: 1524869 (The Pile)

Max Activating Token Index: 935

Text #6

Max Range: 1.0692. Min Range: -1.0692

Max Act: 1.0074. Min Act: -0.0000

Data Index: 1148245 (The Pile)

Max Activating Token Index: 412

Text #7

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7955. Min Act: -0.0000

Data Index: 135448 (The Pile)

Max Activating Token Index: 959

Text #8

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8222. Min Act: -0.0000

Data Index: 935050 (The Pile)

Max Activating Token Index: 935

Text #9

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8374. Min Act: -0.0000

Data Index: 103974 (The Pile)

Max Activating Token Index: 798

Text #10

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.8102. Min Act: -0.0000

Data Index: 6611 (The Pile)

Max Activating Token Index: 1016

Text #11

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7982. Min Act: -0.0000

Data Index: 1309039 (The Pile)

Max Activating Token Index: 387

Text #12

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7889. Min Act: -0.0000

Data Index: 589901 (The Pile)

Max Activating Token Index: 61

Text #13

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7716. Min Act: -0.0000

Data Index: 1981714 (The Pile)

Max Activating Token Index: 432

Text #14

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7960. Min Act: -0.0000

Data Index: 213886 (The Pile)

Max Activating Token Index: 640

Text #15

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1400217 (The Pile)

Max Activating Token Index: 43

Text #16

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7690. Min Act: -0.0000

Data Index: 1828245 (The Pile)

Max Activating Token Index: 444

Text #17

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7608. Min Act: -0.0000

Data Index: 1908153 (The Pile)

Max Activating Token Index: 108

Text #18

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7847. Min Act: -0.0000

Data Index: 836304 (The Pile)

Max Activating Token Index: 395

Text #19

Max Range: 1.0692. Min Range: -1.0692

Max Act: 0.7861. Min Act: -0.0000

Data Index: 187293 (The Pile)

Max Activating Token Index: 903