Model: SoLU Model: 12 Layers, 6144 Neurons per Layer

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

Neuron 3056 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-12l')

Text #0

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.2023. Min Act: -0.0000

Data Index: 1075686 (C4 (Web Text))

Max Activating Token Index: 126

Text #1

Max Range: 1.2023. Min Range: -1.2023

Max Act: 1.1775. Min Act: -0.0000

Data Index: 764628 (C4 (Web Text))

Max Activating Token Index: 174

Text #2

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.9941. Min Act: -0.0000

Data Index: 736960 (C4 (Web Text))

Max Activating Token Index: 325

Text #3

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.9117. Min Act: -0.0000

Data Index: 1283996 (C4 (Web Text))

Max Activating Token Index: 970

Text #4

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.8930. Min Act: -0.0000

Data Index: 715588 (C4 (Web Text))

Max Activating Token Index: 63

Text #5

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.8238. Min Act: -0.0000

Data Index: 1599641 (Python Code)

Max Activating Token Index: 34

Text #6

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7701. Min Act: -0.0000

Data Index: 275527 (C4 (Web Text))

Max Activating Token Index: 281

Text #7

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7522. Min Act: -0.0000

Data Index: 461198 (C4 (Web Text))

Max Activating Token Index: 24

Text #8

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7977. Min Act: -0.0000

Data Index: 1643362 (Python Code)

Max Activating Token Index: 532

Text #9

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7673. Min Act: -0.0000

Data Index: 1018977 (C4 (Web Text))

Max Activating Token Index: 910

Text #10

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7816. Min Act: -0.0000

Data Index: 109171 (C4 (Web Text))

Max Activating Token Index: 870

Text #11

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7433. Min Act: -0.0000

Data Index: 1210121 (C4 (Web Text))

Max Activating Token Index: 53

Text #12

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7258. Min Act: -0.0000

Data Index: 861446 (C4 (Web Text))

Max Activating Token Index: 879

Text #13

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7422. Min Act: -0.0000

Data Index: 84137 (C4 (Web Text))

Max Activating Token Index: 467

Text #14

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.6857. Min Act: -0.0000

Data Index: 155354 (C4 (Web Text))

Max Activating Token Index: 1020

Text #15

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7732. Min Act: -0.0000

Data Index: 561011 (C4 (Web Text))

Max Activating Token Index: 1000

Text #16

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.6702. Min Act: -0.0000

Data Index: 102827 (C4 (Web Text))

Max Activating Token Index: 726

Text #17

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.7321. Min Act: -0.0000

Data Index: 649378 (C4 (Web Text))

Max Activating Token Index: 703

Text #18

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1354390 (C4 (Web Text))

Max Activating Token Index: 861

Text #19

Max Range: 1.2023. Min Range: -1.2023

Max Act: 0.6979. Min Act: -0.0000

Data Index: 47718 (C4 (Web Text))

Max Activating Token Index: 357