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

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

Neuron 2422 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: 2.0002. Min Range: -2.0002

Max Act: 2.0002. Min Act: -0.0000

Data Index: 924594 (C4 (Web Text))

Max Activating Token Index: 144

Text #1

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4166. Min Act: -0.0000

Data Index: 1324528 (C4 (Web Text))

Max Activating Token Index: 688

Text #2

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.4749. Min Act: -0.0000

Data Index: 371060 (C4 (Web Text))

Max Activating Token Index: 726

Text #3

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.2978. Min Act: -0.0000

Data Index: 470500 (C4 (Web Text))

Max Activating Token Index: 662

Text #4

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3258. Min Act: -0.0000

Data Index: 136257 (C4 (Web Text))

Max Activating Token Index: 597

Text #5

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.0734. Min Act: -0.0000

Data Index: 407962 (C4 (Web Text))

Max Activating Token Index: 610

Text #6

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.2758. Min Act: -0.0000

Data Index: 427070 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.2658. Min Act: -0.0000

Data Index: 959356 (C4 (Web Text))

Max Activating Token Index: 149

Text #8

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1851. Min Act: -0.0000

Data Index: 356876 (C4 (Web Text))

Max Activating Token Index: 516

Text #9

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1859. Min Act: -0.0000

Data Index: 515882 (C4 (Web Text))

Max Activating Token Index: 127

Text #10

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1192205 (C4 (Web Text))

Max Activating Token Index: 297

Text #11

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1649. Min Act: -0.0000

Data Index: 673391 (C4 (Web Text))

Max Activating Token Index: 800

Text #12

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1044. Min Act: -0.0000

Data Index: 352802 (C4 (Web Text))

Max Activating Token Index: 708

Text #13

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1960. Min Act: -0.0000

Data Index: 490963 (C4 (Web Text))

Max Activating Token Index: 978

Text #14

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.3250. Min Act: -0.0000

Data Index: 961928 (C4 (Web Text))

Max Activating Token Index: 272

Text #15

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.0886. Min Act: -0.0000

Data Index: 779643 (C4 (Web Text))

Max Activating Token Index: 681

Text #16

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1544. Min Act: -0.0000

Data Index: 977527 (C4 (Web Text))

Max Activating Token Index: 303

Text #17

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1908. Min Act: -0.0000

Data Index: 1103703 (C4 (Web Text))

Max Activating Token Index: 381

Text #18

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.1792. Min Act: -0.0000

Data Index: 1161966 (C4 (Web Text))

Max Activating Token Index: 988

Text #19

Max Range: 2.0002. Min Range: -2.0002

Max Act: 1.2844. Min Act: -0.0000

Data Index: 634928 (C4 (Web Text))

Max Activating Token Index: 712