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

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

Neuron 2008 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.6699. Min Act: -0.0000

Data Index: 643706 (C4 (Web Text))

Max Activating Token Index: 890

Text #1

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.6828. Min Act: -0.0000

Data Index: 104053 (C4 (Web Text))

Max Activating Token Index: 64

Text #2

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3341. Min Act: -0.0000

Data Index: 1207558 (C4 (Web Text))

Max Activating Token Index: 836

Text #3

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3778. Min Act: -0.0000

Data Index: 138457 (C4 (Web Text))

Max Activating Token Index: 847

Text #4

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.4487. Min Act: -0.0000

Data Index: 479627 (C4 (Web Text))

Max Activating Token Index: 294

Text #5

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.5314. Min Act: -0.0000

Data Index: 773504 (C4 (Web Text))

Max Activating Token Index: 871

Text #6

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.5383. Min Act: -0.0000

Data Index: 322411 (C4 (Web Text))

Max Activating Token Index: 820

Text #7

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.4032. Min Act: -0.0000

Data Index: 827649 (C4 (Web Text))

Max Activating Token Index: 48

Text #8

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3572. Min Act: -0.0000

Data Index: 75681 (C4 (Web Text))

Max Activating Token Index: 500

Text #9

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.4085. Min Act: -0.0000

Data Index: 597566 (C4 (Web Text))

Max Activating Token Index: 689

Text #10

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.2645. Min Act: -0.0000

Data Index: 381268 (C4 (Web Text))

Max Activating Token Index: 408

Text #11

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.1848. Min Act: -0.0000

Data Index: 650137 (C4 (Web Text))

Max Activating Token Index: 353

Text #12

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3292. Min Act: -0.0000

Data Index: 710409 (C4 (Web Text))

Max Activating Token Index: 396

Text #13

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.4122. Min Act: -0.0000

Data Index: 178364 (C4 (Web Text))

Max Activating Token Index: 351

Text #14

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.1442. Min Act: -0.0000

Data Index: 876333 (C4 (Web Text))

Max Activating Token Index: 277

Text #15

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3068. Min Act: -0.0000

Data Index: 1225677 (C4 (Web Text))

Max Activating Token Index: 993

Text #16

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3848. Min Act: -0.0000

Data Index: 611356 (C4 (Web Text))

Max Activating Token Index: 140

Text #17

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.3810. Min Act: -0.0000

Data Index: 1034843 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.2673. Min Act: -0.0000

Data Index: 144126 (C4 (Web Text))

Max Activating Token Index: 760

Text #19

Max Range: 1.6828. Min Range: -1.6828

Max Act: 1.1952. Min Act: -0.0000

Data Index: 135957 (C4 (Web Text))

Max Activating Token Index: 950