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

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

Neuron 2316 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 4.1025. Min Range: -4.1025

Max Act: 4.1025. Min Act: -0.0000

Data Index: 328680 (C4 (Web Text))

Max Activating Token Index: 212

Text #1

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.5690. Min Act: -0.0000

Data Index: 878685 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.7166. Min Act: -0.0001

Data Index: 993831 (C4 (Web Text))

Max Activating Token Index: 317

Text #3

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.5996. Min Act: -0.0000

Data Index: 800948 (C4 (Web Text))

Max Activating Token Index: 66

Text #4

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.7495. Min Act: -0.0000

Data Index: 766909 (C4 (Web Text))

Max Activating Token Index: 426

Text #5

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.8910. Min Act: -0.0000

Data Index: 820222 (C4 (Web Text))

Max Activating Token Index: 771

Text #6

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.9664. Min Act: -0.0000

Data Index: 157067 (C4 (Web Text))

Max Activating Token Index: 573

Text #7

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.7512. Min Act: -0.0000

Data Index: 58795 (C4 (Web Text))

Max Activating Token Index: 1018

Text #8

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.1250. Min Act: -0.0000

Data Index: 592067 (C4 (Web Text))

Max Activating Token Index: 260

Text #9

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.5921. Min Act: -0.0001

Data Index: 133813 (C4 (Web Text))

Max Activating Token Index: 253

Text #10

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.9778. Min Act: -0.0000

Data Index: 61409 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.9788. Min Act: -0.0000

Data Index: 630891 (C4 (Web Text))

Max Activating Token Index: 58

Text #12

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.6746. Min Act: -0.0000

Data Index: 359745 (C4 (Web Text))

Max Activating Token Index: 93

Text #13

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.0464. Min Act: -0.0000

Data Index: 433938 (C4 (Web Text))

Max Activating Token Index: 180

Text #14

Max Range: 4.1025. Min Range: -4.1025

Max Act: 3.1758. Min Act: -0.0001

Data Index: 607609 (C4 (Web Text))

Max Activating Token Index: 156

Text #15

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.6356. Min Act: -0.0000

Data Index: 943591 (C4 (Web Text))

Max Activating Token Index: 61

Text #16

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.7143. Min Act: -0.0000

Data Index: 1122626 (C4 (Web Text))

Max Activating Token Index: 205

Text #17

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.7851. Min Act: -0.0000

Data Index: 493800 (C4 (Web Text))

Max Activating Token Index: 244

Text #18

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.6679. Min Act: -0.0001

Data Index: 357012 (C4 (Web Text))

Max Activating Token Index: 424

Text #19

Max Range: 4.1025. Min Range: -4.1025

Max Act: 2.5311. Min Act: -0.0000

Data Index: 1162554 (C4 (Web Text))

Max Activating Token Index: 353