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

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

Neuron 3356 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2813. Min Act: -0.0000

Data Index: 97404 (C4 (Web Text))

Max Activating Token Index: 943

Text #1

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2423. Min Act: -0.0000

Data Index: 912473 (C4 (Web Text))

Max Activating Token Index: 164

Text #2

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2183. Min Act: -0.0000

Data Index: 616223 (C4 (Web Text))

Max Activating Token Index: 672

Text #3

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2119. Min Act: -0.0000

Data Index: 240956 (C4 (Web Text))

Max Activating Token Index: 253

Text #4

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2116. Min Act: -0.0000

Data Index: 660570 (C4 (Web Text))

Max Activating Token Index: 393

Text #5

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.2029. Min Act: -0.0000

Data Index: 559944 (C4 (Web Text))

Max Activating Token Index: 679

Text #6

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1838. Min Act: -0.0000

Data Index: 666144 (C4 (Web Text))

Max Activating Token Index: 223

Text #7

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1949. Min Act: -0.0000

Data Index: 867472 (C4 (Web Text))

Max Activating Token Index: 698

Text #8

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1937. Min Act: -0.0000

Data Index: 1299032 (C4 (Web Text))

Max Activating Token Index: 528

Text #9

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1834. Min Act: -0.0000

Data Index: 236379 (C4 (Web Text))

Max Activating Token Index: 460

Text #10

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1969. Min Act: -0.0000

Data Index: 1006878 (C4 (Web Text))

Max Activating Token Index: 987

Text #11

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1928. Min Act: -0.0000

Data Index: 1357999 (C4 (Web Text))

Max Activating Token Index: 578

Text #12

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1850. Min Act: -0.0000

Data Index: 1348046 (C4 (Web Text))

Max Activating Token Index: 441

Text #13

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1837. Min Act: -0.0000

Data Index: 1354048 (C4 (Web Text))

Max Activating Token Index: 404

Text #14

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1776. Min Act: -0.0000

Data Index: 505531 (C4 (Web Text))

Max Activating Token Index: 710

Text #15

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1783. Min Act: -0.0000

Data Index: 1140906 (C4 (Web Text))

Max Activating Token Index: 1004

Text #16

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1805. Min Act: -0.0000

Data Index: 108140 (C4 (Web Text))

Max Activating Token Index: 550

Text #17

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1814. Min Act: -0.0000

Data Index: 1359326 (C4 (Web Text))

Max Activating Token Index: 910

Text #18

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1732. Min Act: -0.0000

Data Index: 979823 (C4 (Web Text))

Max Activating Token Index: 197

Text #19

Max Range: 0.2813. Min Range: -0.2813

Max Act: 0.1811. Min Act: -0.0000

Data Index: 346508 (C4 (Web Text))

Max Activating Token Index: 411