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

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

Neuron 1924 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: 0.7273. Min Range: -0.7273

Max Act: 0.7273. Min Act: -0.0000

Data Index: 1310525 (C4 (Web Text))

Max Activating Token Index: 914

Text #1

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6190. Min Act: -0.0000

Data Index: 827477 (C4 (Web Text))

Max Activating Token Index: 131

Text #2

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6367. Min Act: -0.0000

Data Index: 156198 (C4 (Web Text))

Max Activating Token Index: 82

Text #3

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6250. Min Act: -0.0000

Data Index: 936770 (C4 (Web Text))

Max Activating Token Index: 109

Text #4

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.6214. Min Act: -0.0000

Data Index: 1296449 (C4 (Web Text))

Max Activating Token Index: 494

Text #5

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5989. Min Act: -0.0000

Data Index: 1484729 (Python Code)

Max Activating Token Index: 559

Text #6

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5891. Min Act: -0.0000

Data Index: 615934 (C4 (Web Text))

Max Activating Token Index: 52

Text #7

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5503. Min Act: -0.0000

Data Index: 1563897 (Python Code)

Max Activating Token Index: 753

Text #8

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5682. Min Act: -0.0000

Data Index: 973829 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1013364 (C4 (Web Text))

Max Activating Token Index: 854

Text #10

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5524. Min Act: -0.0000

Data Index: 699979 (C4 (Web Text))

Max Activating Token Index: 818

Text #11

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5403. Min Act: -0.0000

Data Index: 1480935 (Python Code)

Max Activating Token Index: 992

Text #12

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5204. Min Act: -0.0000

Data Index: 1575017 (Python Code)

Max Activating Token Index: 995

Text #13

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5102. Min Act: -0.0000

Data Index: 647591 (C4 (Web Text))

Max Activating Token Index: 851

Text #14

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5475. Min Act: -0.0000

Data Index: 1553912 (Python Code)

Max Activating Token Index: 293

Text #15

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5022. Min Act: -0.0000

Data Index: 1027172 (C4 (Web Text))

Max Activating Token Index: 925

Text #16

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.4914. Min Act: -0.0000

Data Index: 1401282 (Python Code)

Max Activating Token Index: 895

Text #17

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5068. Min Act: -0.0000

Data Index: 1079677 (C4 (Web Text))

Max Activating Token Index: 754

Text #18

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.5085. Min Act: -0.0000

Data Index: 750494 (C4 (Web Text))

Max Activating Token Index: 926

Text #19

Max Range: 0.7273. Min Range: -0.7273

Max Act: 0.4645. Min Act: -0.0000

Data Index: 2499 (C4 (Web Text))

Max Activating Token Index: 892