Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 4722 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3836. Min Act: -0.0000

Data Index: 296419 (C4 (Web Text))

Max Activating Token Index: 722

Text #1

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3573. Min Act: -0.0000

Data Index: 968731 (C4 (Web Text))

Max Activating Token Index: 223

Text #2

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3458. Min Act: -0.0000

Data Index: 411269 (C4 (Web Text))

Max Activating Token Index: 486

Text #3

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3439. Min Act: -0.0000

Data Index: 525242 (C4 (Web Text))

Max Activating Token Index: 668

Text #4

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3417. Min Act: -0.0000

Data Index: 1110816 (C4 (Web Text))

Max Activating Token Index: 219

Text #5

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3469. Min Act: -0.0000

Data Index: 1034994 (C4 (Web Text))

Max Activating Token Index: 955

Text #6

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.3405. Min Act: -0.0000

Data Index: 699387 (C4 (Web Text))

Max Activating Token Index: 91

Text #7

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2757. Min Act: -0.0000

Data Index: 198637 (C4 (Web Text))

Max Activating Token Index: 128

Text #8

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2806. Min Act: -0.0000

Data Index: 273127 (C4 (Web Text))

Max Activating Token Index: 543

Text #9

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2072. Min Act: -0.0000

Data Index: 925683 (C4 (Web Text))

Max Activating Token Index: 939

Text #10

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2148. Min Act: -0.0000

Data Index: 358757 (C4 (Web Text))

Max Activating Token Index: 746

Text #11

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1972. Min Act: -0.0000

Data Index: 419914 (C4 (Web Text))

Max Activating Token Index: 495

Text #12

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.2040. Min Act: -0.0000

Data Index: 884419 (C4 (Web Text))

Max Activating Token Index: 916

Text #13

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1930. Min Act: -0.0000

Data Index: 959951 (C4 (Web Text))

Max Activating Token Index: 63

Text #14

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1857. Min Act: -0.0000

Data Index: 1170168 (C4 (Web Text))

Max Activating Token Index: 315

Text #15

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1936. Min Act: -0.0000

Data Index: 463553 (C4 (Web Text))

Max Activating Token Index: 329

Text #16

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1864. Min Act: -0.0000

Data Index: 871273 (C4 (Web Text))

Max Activating Token Index: 544

Text #17

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1835. Min Act: -0.0000

Data Index: 575148 (C4 (Web Text))

Max Activating Token Index: 328

Text #18

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1824. Min Act: -0.0000

Data Index: 1162771 (C4 (Web Text))

Max Activating Token Index: 960

Text #19

Max Range: 0.3836. Min Range: -0.3836

Max Act: 0.1743. Min Act: -0.0000

Data Index: 1053862 (C4 (Web Text))

Max Activating Token Index: 523