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

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

Neuron 1970 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: 2.7057. Min Range: -2.7057

Max Act: 2.7057. Min Act: -0.0000

Data Index: 374724 (C4 (Web Text))

Max Activating Token Index: 311

Text #1

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.2243. Min Act: -0.0000

Data Index: 615130 (C4 (Web Text))

Max Activating Token Index: 644

Text #2

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.1632. Min Act: -0.0000

Data Index: 782516 (C4 (Web Text))

Max Activating Token Index: 871

Text #3

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.0360. Min Act: -0.0000

Data Index: 1099826 (C4 (Web Text))

Max Activating Token Index: 806

Text #4

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.1851. Min Act: -0.0000

Data Index: 906052 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.0439. Min Act: -0.0000

Data Index: 526120 (C4 (Web Text))

Max Activating Token Index: 786

Text #6

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.1019. Min Act: -0.0000

Data Index: 268123 (C4 (Web Text))

Max Activating Token Index: 54

Text #7

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.0016. Min Act: -0.0000

Data Index: 1322590 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.9763. Min Act: -0.0000

Data Index: 893910 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.0836. Min Act: -0.0000

Data Index: 103978 (C4 (Web Text))

Max Activating Token Index: 574

Text #10

Max Range: 2.7057. Min Range: -2.7057

Max Act: 2.0652. Min Act: -0.0000

Data Index: 350983 (C4 (Web Text))

Max Activating Token Index: 827

Text #11

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.9518. Min Act: -0.0000

Data Index: 1001145 (C4 (Web Text))

Max Activating Token Index: 591

Text #12

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.7991. Min Act: -0.0000

Data Index: 278702 (C4 (Web Text))

Max Activating Token Index: 664

Text #13

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.8989. Min Act: -0.0000

Data Index: 286878 (C4 (Web Text))

Max Activating Token Index: 813

Text #14

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.8063. Min Act: -0.0000

Data Index: 633561 (C4 (Web Text))

Max Activating Token Index: 946

Text #15

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.7826. Min Act: -0.0000

Data Index: 1022994 (C4 (Web Text))

Max Activating Token Index: 269

Text #16

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.8081. Min Act: -0.0000

Data Index: 706508 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.7848. Min Act: -0.0000

Data Index: 1195292 (C4 (Web Text))

Max Activating Token Index: 851

Text #18

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.8167. Min Act: -0.0000

Data Index: 1332757 (C4 (Web Text))

Max Activating Token Index: 176

Text #19

Max Range: 2.7057. Min Range: -2.7057

Max Act: 1.8875. Min Act: -0.0000

Data Index: 1120775 (C4 (Web Text))

Max Activating Token Index: 730