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

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

Neuron 3767 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: 1.9813. Min Range: -1.9813

Max Act: 1.9813. Min Act: -0.0000

Data Index: 830615 (C4 (Web Text))

Max Activating Token Index: 323

Text #1

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.7856. Min Act: -0.0000

Data Index: 899397 (C4 (Web Text))

Max Activating Token Index: 816

Text #2

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.7551. Min Act: -0.0000

Data Index: 1255557 (C4 (Web Text))

Max Activating Token Index: 848

Text #3

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5595. Min Act: -0.0000

Data Index: 1139206 (C4 (Web Text))

Max Activating Token Index: 981

Text #4

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.6303. Min Act: -0.0000

Data Index: 47891 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5844. Min Act: -0.0000

Data Index: 826947 (C4 (Web Text))

Max Activating Token Index: 483

Text #6

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5816. Min Act: 0.0000

Data Index: 644525 (C4 (Web Text))

Max Activating Token Index: 836

Text #7

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4928. Min Act: -0.0000

Data Index: 268426 (C4 (Web Text))

Max Activating Token Index: 56

Text #8

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5380. Min Act: -0.0000

Data Index: 1348403 (C4 (Web Text))

Max Activating Token Index: 706

Text #9

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5372. Min Act: -0.0000

Data Index: 650736 (C4 (Web Text))

Max Activating Token Index: 209

Text #10

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5189. Min Act: -0.0000

Data Index: 846054 (C4 (Web Text))

Max Activating Token Index: 400

Text #11

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.5115. Min Act: -0.0000

Data Index: 882376 (C4 (Web Text))

Max Activating Token Index: 408

Text #12

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4792. Min Act: -0.0000

Data Index: 850744 (C4 (Web Text))

Max Activating Token Index: 343

Text #13

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4716. Min Act: -0.0000

Data Index: 1314334 (C4 (Web Text))

Max Activating Token Index: 1008

Text #14

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4478. Min Act: -0.0000

Data Index: 1128138 (C4 (Web Text))

Max Activating Token Index: 819

Text #15

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4426. Min Act: -0.0000

Data Index: 823105 (C4 (Web Text))

Max Activating Token Index: 416

Text #16

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4245. Min Act: -0.0000

Data Index: 1522343 (Python Code)

Max Activating Token Index: 449

Text #17

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.4160. Min Act: 0.0000

Data Index: 427212 (C4 (Web Text))

Max Activating Token Index: 625

Text #18

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.3309. Min Act: -0.0000

Data Index: 64132 (C4 (Web Text))

Max Activating Token Index: 915

Text #19

Max Range: 1.9813. Min Range: -1.9813

Max Act: 1.3174. Min Act: -0.0000

Data Index: 507585 (C4 (Web Text))

Max Activating Token Index: 90