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

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

Neuron 4747 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.9623. Min Act: -0.0000

Data Index: 1036612 (C4 (Web Text))

Max Activating Token Index: 93

Text #1

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.8534. Min Act: -0.0000

Data Index: 149646 (C4 (Web Text))

Max Activating Token Index: 755

Text #2

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5352. Min Act: -0.0000

Data Index: 364313 (C4 (Web Text))

Max Activating Token Index: 233

Text #3

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5311. Min Act: -0.0000

Data Index: 307197 (C4 (Web Text))

Max Activating Token Index: 696

Text #4

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5090. Min Act: -0.0000

Data Index: 619998 (C4 (Web Text))

Max Activating Token Index: 908

Text #5

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5027. Min Act: -0.0000

Data Index: 974198 (C4 (Web Text))

Max Activating Token Index: 40

Text #6

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5392. Min Act: -0.0000

Data Index: 289966 (C4 (Web Text))

Max Activating Token Index: 512

Text #7

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.4887. Min Act: -0.0000

Data Index: 335121 (C4 (Web Text))

Max Activating Token Index: 42

Text #8

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.3735. Min Act: -0.0000

Data Index: 1188157 (C4 (Web Text))

Max Activating Token Index: 799

Text #9

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5297. Min Act: -0.0000

Data Index: 685444 (C4 (Web Text))

Max Activating Token Index: 808

Text #10

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.4411. Min Act: -0.0000

Data Index: 230888 (C4 (Web Text))

Max Activating Token Index: 194

Text #11

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.3975. Min Act: -0.0000

Data Index: 474835 (C4 (Web Text))

Max Activating Token Index: 118

Text #12

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.5129. Min Act: -0.0000

Data Index: 945623 (C4 (Web Text))

Max Activating Token Index: 30

Text #13

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.4275. Min Act: -0.0000

Data Index: 895922 (C4 (Web Text))

Max Activating Token Index: 45

Text #14

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.4681. Min Act: -0.0000

Data Index: 730796 (C4 (Web Text))

Max Activating Token Index: 432

Text #15

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.3601. Min Act: -0.0000

Data Index: 371500 (C4 (Web Text))

Max Activating Token Index: 160

Text #16

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.3817. Min Act: -0.0000

Data Index: 930049 (C4 (Web Text))

Max Activating Token Index: 366

Text #17

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.2849. Min Act: -0.0000

Data Index: 482047 (C4 (Web Text))

Max Activating Token Index: 915

Text #18

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.3704. Min Act: -0.0000

Data Index: 92251 (C4 (Web Text))

Max Activating Token Index: 455

Text #19

Max Range: 1.9623. Min Range: -1.9623

Max Act: 1.3910. Min Act: -0.0000

Data Index: 952658 (C4 (Web Text))

Max Activating Token Index: 346