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

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

Neuron 1320 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.9054. Min Act: -0.0000

Data Index: 907715 (C4 (Web Text))

Max Activating Token Index: 33

Text #1

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7916. Min Act: -0.0000

Data Index: 58142 (C4 (Web Text))

Max Activating Token Index: 47

Text #2

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7848. Min Act: -0.0000

Data Index: 165185 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7901. Min Act: -0.0000

Data Index: 1297084 (C4 (Web Text))

Max Activating Token Index: 39

Text #4

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7452. Min Act: -0.0000

Data Index: 230886 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7701. Min Act: -0.0000

Data Index: 322826 (C4 (Web Text))

Max Activating Token Index: 660

Text #6

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.8503. Min Act: -0.0000

Data Index: 159822 (C4 (Web Text))

Max Activating Token Index: 863

Text #7

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7568. Min Act: -0.0000

Data Index: 77874 (C4 (Web Text))

Max Activating Token Index: 23

Text #8

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7307. Min Act: -0.0000

Data Index: 519787 (C4 (Web Text))

Max Activating Token Index: 620

Text #9

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7500. Min Act: -0.0000

Data Index: 1231575 (C4 (Web Text))

Max Activating Token Index: 281

Text #10

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7238. Min Act: -0.0000

Data Index: 1092188 (C4 (Web Text))

Max Activating Token Index: 925

Text #11

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7434. Min Act: -0.0000

Data Index: 1352552 (C4 (Web Text))

Max Activating Token Index: 659

Text #12

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7431. Min Act: -0.0000

Data Index: 310275 (C4 (Web Text))

Max Activating Token Index: 530

Text #13

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7779. Min Act: -0.0000

Data Index: 572562 (C4 (Web Text))

Max Activating Token Index: 892

Text #14

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.6921. Min Act: -0.0000

Data Index: 87494 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7555. Min Act: -0.0000

Data Index: 96365 (C4 (Web Text))

Max Activating Token Index: 365

Text #16

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7356. Min Act: -0.0000

Data Index: 996551 (C4 (Web Text))

Max Activating Token Index: 289

Text #17

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7547. Min Act: -0.0000

Data Index: 111292 (C4 (Web Text))

Max Activating Token Index: 72

Text #18

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7564. Min Act: -0.0000

Data Index: 1148572 (C4 (Web Text))

Max Activating Token Index: 807

Text #19

Max Range: 0.9054. Min Range: -0.9054

Max Act: 0.7284. Min Act: -0.0000

Data Index: 829798 (C4 (Web Text))

Max Activating Token Index: 7