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

Dataset: The Pile

Neuron 1907 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7998. Min Act: -0.0000

Data Index: 367480 (The Pile)

Max Activating Token Index: 42

Text #1

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.7892. Min Act: -0.0000

Data Index: 1794155 (The Pile)

Max Activating Token Index: 124

Text #2

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.6023. Min Act: -0.0000

Data Index: 475837 (The Pile)

Max Activating Token Index: 725

Text #3

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1835822 (The Pile)

Max Activating Token Index: 936

Text #4

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5586. Min Act: 0.0000

Data Index: 448832 (The Pile)

Max Activating Token Index: 534

Text #5

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1328184 (The Pile)

Max Activating Token Index: 324

Text #6

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4979. Min Act: -0.0000

Data Index: 645879 (The Pile)

Max Activating Token Index: 181

Text #7

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5206. Min Act: -0.0000

Data Index: 553429 (The Pile)

Max Activating Token Index: 989

Text #8

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4867. Min Act: -0.0000

Data Index: 456315 (The Pile)

Max Activating Token Index: 61

Text #9

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.5073. Min Act: 0.0000

Data Index: 231099 (The Pile)

Max Activating Token Index: 483

Text #10

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4729. Min Act: 0.0000

Data Index: 1705029 (The Pile)

Max Activating Token Index: 152

Text #11

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4770. Min Act: 0.0000

Data Index: 1089566 (The Pile)

Max Activating Token Index: 231

Text #12

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4599. Min Act: -0.0000

Data Index: 1962478 (The Pile)

Max Activating Token Index: 451

Text #13

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4520. Min Act: -0.0000

Data Index: 1469215 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4440. Min Act: -0.0000

Data Index: 519336 (The Pile)

Max Activating Token Index: 130

Text #15

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4421. Min Act: 0.0000

Data Index: 1354533 (The Pile)

Max Activating Token Index: 586

Text #16

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4267. Min Act: -0.0000

Data Index: 1224586 (The Pile)

Max Activating Token Index: 612

Text #17

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.3979. Min Act: 0.0000

Data Index: 1605273 (The Pile)

Max Activating Token Index: 692

Text #18

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4283. Min Act: -0.0000

Data Index: 1683443 (The Pile)

Max Activating Token Index: 23

Text #19

Max Range: 0.7998. Min Range: -0.7998

Max Act: 0.4447. Min Act: -0.0000

Data Index: 1993492 (The Pile)

Max Activating Token Index: 647