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

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

Neuron 1970 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: 0.7909. Min Range: -0.7909

Max Act: 0.7909. Min Act: -0.0000

Data Index: 1176220 (C4 (Web Text))

Max Activating Token Index: 880

Text #1

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6550. Min Act: -0.0000

Data Index: 397716 (C4 (Web Text))

Max Activating Token Index: 769

Text #2

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6479. Min Act: -0.0000

Data Index: 243956 (C4 (Web Text))

Max Activating Token Index: 85

Text #3

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6371. Min Act: -0.0000

Data Index: 647068 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6231. Min Act: -0.0000

Data Index: 1175444 (C4 (Web Text))

Max Activating Token Index: 325

Text #5

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6218. Min Act: -0.0000

Data Index: 544226 (C4 (Web Text))

Max Activating Token Index: 727

Text #6

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6607. Min Act: -0.0000

Data Index: 954167 (C4 (Web Text))

Max Activating Token Index: 854

Text #7

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6145. Min Act: -0.0000

Data Index: 865645 (C4 (Web Text))

Max Activating Token Index: 632

Text #8

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6145. Min Act: -0.0000

Data Index: 1268880 (C4 (Web Text))

Max Activating Token Index: 191

Text #9

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6095. Min Act: -0.0000

Data Index: 383294 (C4 (Web Text))

Max Activating Token Index: 564

Text #10

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1295251 (C4 (Web Text))

Max Activating Token Index: 1012

Text #11

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.6117. Min Act: -0.0000

Data Index: 1138608 (C4 (Web Text))

Max Activating Token Index: 240

Text #12

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5679. Min Act: -0.0000

Data Index: 237069 (C4 (Web Text))

Max Activating Token Index: 40

Text #13

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5572. Min Act: -0.0000

Data Index: 710023 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5826. Min Act: -0.0000

Data Index: 1055993 (C4 (Web Text))

Max Activating Token Index: 913

Text #15

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5603. Min Act: -0.0000

Data Index: 543072 (C4 (Web Text))

Max Activating Token Index: 695

Text #16

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5361. Min Act: -0.0000

Data Index: 975233 (C4 (Web Text))

Max Activating Token Index: 932

Text #17

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5475. Min Act: -0.0000

Data Index: 932881 (C4 (Web Text))

Max Activating Token Index: 66

Text #18

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5417. Min Act: -0.0000

Data Index: 1029511 (C4 (Web Text))

Max Activating Token Index: 230

Text #19

Max Range: 0.7909. Min Range: -0.7909

Max Act: 0.5562. Min Act: -0.0000

Data Index: 5459 (C4 (Web Text))

Max Activating Token Index: 171