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

Dataset: The Pile

Neuron 2675 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: 0.9289. Min Range: -0.9289

Max Act: 0.8808. Min Act: -0.0000

Data Index: 915977 (The Pile)

Max Activating Token Index: 795

Text #1

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.9289. Min Act: -0.0000

Data Index: 1201262 (The Pile)

Max Activating Token Index: 523

Text #2

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.8082. Min Act: -0.0000

Data Index: 1666173 (The Pile)

Max Activating Token Index: 276

Text #3

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7941. Min Act: -0.0000

Data Index: 1821012 (The Pile)

Max Activating Token Index: 1000

Text #4

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7650. Min Act: -0.0000

Data Index: 1765261 (The Pile)

Max Activating Token Index: 232

Text #5

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7371. Min Act: -0.0000

Data Index: 436587 (The Pile)

Max Activating Token Index: 725

Text #6

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7589. Min Act: -0.0000

Data Index: 47707 (The Pile)

Max Activating Token Index: 161

Text #7

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7632. Min Act: -0.0000

Data Index: 1885559 (The Pile)

Max Activating Token Index: 723

Text #8

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7155. Min Act: -0.0000

Data Index: 1970640 (The Pile)

Max Activating Token Index: 137

Text #9

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7070. Min Act: -0.0000

Data Index: 1478328 (The Pile)

Max Activating Token Index: 47

Text #10

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6431. Min Act: -0.0000

Data Index: 1085144 (The Pile)

Max Activating Token Index: 104

Text #11

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7265. Min Act: -0.0000

Data Index: 452520 (The Pile)

Max Activating Token Index: 318

Text #12

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6686. Min Act: -0.0000

Data Index: 1167302 (The Pile)

Max Activating Token Index: 34

Text #13

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1087837 (The Pile)

Max Activating Token Index: 148

Text #14

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.7000. Min Act: -0.0000

Data Index: 1393531 (The Pile)

Max Activating Token Index: 53

Text #15

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6626. Min Act: -0.0000

Data Index: 629059 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6740. Min Act: -0.0000

Data Index: 496820 (The Pile)

Max Activating Token Index: 493

Text #17

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6907. Min Act: -0.0000

Data Index: 1987855 (The Pile)

Max Activating Token Index: 743

Text #18

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6981. Min Act: -0.0000

Data Index: 1682448 (The Pile)

Max Activating Token Index: 540

Text #19

Max Range: 0.9289. Min Range: -0.9289

Max Act: 0.6743. Min Act: -0.0000

Data Index: 718568 (The Pile)

Max Activating Token Index: 210