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

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

Neuron 881 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 2.0242. Min Range: -2.0242

Max Act: 2.0242. Min Act: 0.0001

Data Index: 771875 (C4 (Web Text))

Max Activating Token Index: 77

Text #1

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.5843. Min Act: 0.0001

Data Index: 836602 (C4 (Web Text))

Max Activating Token Index: 22

Text #2

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.5694. Min Act: -0.0000

Data Index: 802906 (C4 (Web Text))

Max Activating Token Index: 853

Text #3

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.6326. Min Act: -0.0000

Data Index: 37893 (C4 (Web Text))

Max Activating Token Index: 328

Text #4

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.4753. Min Act: 0.0000

Data Index: 643531 (C4 (Web Text))

Max Activating Token Index: 163

Text #5

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.4229. Min Act: 0.0000

Data Index: 43220 (C4 (Web Text))

Max Activating Token Index: 98

Text #6

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.4122. Min Act: -0.0000

Data Index: 1101341 (C4 (Web Text))

Max Activating Token Index: 640

Text #7

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3106. Min Act: 0.0000

Data Index: 878465 (C4 (Web Text))

Max Activating Token Index: 204

Text #8

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3124. Min Act: 0.0000

Data Index: 453849 (C4 (Web Text))

Max Activating Token Index: 246

Text #9

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3763. Min Act: -0.0000

Data Index: 1063773 (C4 (Web Text))

Max Activating Token Index: 598

Text #10

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3363. Min Act: -0.0000

Data Index: 35588 (C4 (Web Text))

Max Activating Token Index: 911

Text #11

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3238. Min Act: 0.0001

Data Index: 303472 (C4 (Web Text))

Max Activating Token Index: 154

Text #12

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3138. Min Act: 0.0000

Data Index: 437193 (C4 (Web Text))

Max Activating Token Index: 225

Text #13

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.2976. Min Act: -0.0000

Data Index: 583487 (C4 (Web Text))

Max Activating Token Index: 460

Text #14

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.2801. Min Act: 0.0001

Data Index: 978294 (C4 (Web Text))

Max Activating Token Index: 592

Text #15

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.2835. Min Act: 0.0000

Data Index: 697896 (C4 (Web Text))

Max Activating Token Index: 106

Text #16

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.2829. Min Act: 0.0002

Data Index: 874761 (C4 (Web Text))

Max Activating Token Index: 40

Text #17

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.3535. Min Act: -0.0000

Data Index: 1441773 (Python Code)

Max Activating Token Index: 113

Text #18

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.2731. Min Act: -0.0000

Data Index: 1243190 (C4 (Web Text))

Max Activating Token Index: 33

Text #19

Max Range: 2.0242. Min Range: -2.0242

Max Act: 1.2009. Min Act: 0.0000

Data Index: 1035131 (C4 (Web Text))

Max Activating Token Index: 1022