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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 2265 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.3289. Min Act: -0.0000

Data Index: 737653 (C4 (Web Text))

Max Activating Token Index: 197

Text #1

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2067. Min Act: -0.0000

Data Index: 673043 (C4 (Web Text))

Max Activating Token Index: 629

Text #2

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2154. Min Act: -0.0000

Data Index: 405016 (C4 (Web Text))

Max Activating Token Index: 55

Text #3

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2277. Min Act: -0.0000

Data Index: 884992 (C4 (Web Text))

Max Activating Token Index: 154

Text #4

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2072. Min Act: -0.0000

Data Index: 84914 (C4 (Web Text))

Max Activating Token Index: 932

Text #5

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2088. Min Act: -0.0000

Data Index: 498762 (C4 (Web Text))

Max Activating Token Index: 46

Text #6

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1755. Min Act: -0.0000

Data Index: 749207 (C4 (Web Text))

Max Activating Token Index: 119

Text #7

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.2062. Min Act: -0.0000

Data Index: 939321 (C4 (Web Text))

Max Activating Token Index: 410

Text #8

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1807. Min Act: -0.0000

Data Index: 1226885 (C4 (Web Text))

Max Activating Token Index: 654

Text #9

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1965. Min Act: -0.0000

Data Index: 1147266 (C4 (Web Text))

Max Activating Token Index: 33

Text #10

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1897. Min Act: -0.0000

Data Index: 1342618 (C4 (Web Text))

Max Activating Token Index: 547

Text #11

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1895. Min Act: -0.0000

Data Index: 430696 (C4 (Web Text))

Max Activating Token Index: 496

Text #12

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1729. Min Act: -0.0000

Data Index: 118886 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1867. Min Act: -0.0000

Data Index: 1027432 (C4 (Web Text))

Max Activating Token Index: 987

Text #14

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1732. Min Act: -0.0000

Data Index: 1490640 (Python Code)

Max Activating Token Index: 763

Text #15

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1845. Min Act: -0.0000

Data Index: 903112 (C4 (Web Text))

Max Activating Token Index: 641

Text #16

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1636447 (Python Code)

Max Activating Token Index: 376

Text #17

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1729. Min Act: -0.0000

Data Index: 282983 (C4 (Web Text))

Max Activating Token Index: 839

Text #18

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1834. Min Act: -0.0000

Data Index: 435021 (C4 (Web Text))

Max Activating Token Index: 111

Text #19

Max Range: 0.3289. Min Range: -0.3289

Max Act: 0.1622. Min Act: -0.0000

Data Index: 653149 (C4 (Web Text))

Max Activating Token Index: 841