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

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

Neuron 2777 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: 2.8898. Min Range: -2.8898

Max Act: 2.8898. Min Act: -0.0000

Data Index: 518505 (C4 (Web Text))

Max Activating Token Index: 622

Text #1

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.5020. Min Act: -0.0000

Data Index: 530428 (C4 (Web Text))

Max Activating Token Index: 870

Text #2

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.3079. Min Act: -0.0000

Data Index: 664468 (C4 (Web Text))

Max Activating Token Index: 981

Text #3

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.1774. Min Act: -0.0000

Data Index: 85310 (C4 (Web Text))

Max Activating Token Index: 744

Text #4

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.4136. Min Act: -0.0000

Data Index: 257868 (C4 (Web Text))

Max Activating Token Index: 723

Text #5

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.2627. Min Act: -0.0000

Data Index: 1281847 (C4 (Web Text))

Max Activating Token Index: 983

Text #6

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.2111. Min Act: -0.0000

Data Index: 845442 (C4 (Web Text))

Max Activating Token Index: 493

Text #7

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.1867. Min Act: -0.0000

Data Index: 6400 (C4 (Web Text))

Max Activating Token Index: 591

Text #8

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.1302. Min Act: -0.0000

Data Index: 1065547 (C4 (Web Text))

Max Activating Token Index: 158

Text #9

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.0593. Min Act: -0.0000

Data Index: 1039228 (C4 (Web Text))

Max Activating Token Index: 822

Text #10

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.0518. Min Act: -0.0000

Data Index: 300087 (C4 (Web Text))

Max Activating Token Index: 180

Text #11

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.0021. Min Act: -0.0000

Data Index: 8420 (C4 (Web Text))

Max Activating Token Index: 424

Text #12

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.9639. Min Act: -0.0000

Data Index: 337341 (C4 (Web Text))

Max Activating Token Index: 942

Text #13

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.9443. Min Act: -0.0000

Data Index: 718925 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 2.8898. Min Range: -2.8898

Max Act: 2.0354. Min Act: -0.0000

Data Index: 389729 (C4 (Web Text))

Max Activating Token Index: 680

Text #15

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.9224. Min Act: -0.0000

Data Index: 932527 (C4 (Web Text))

Max Activating Token Index: 167

Text #16

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.8216. Min Act: -0.0000

Data Index: 1329787 (C4 (Web Text))

Max Activating Token Index: 386

Text #17

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.8979. Min Act: -0.0000

Data Index: 753818 (C4 (Web Text))

Max Activating Token Index: 776

Text #18

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.8972. Min Act: -0.0000

Data Index: 216492 (C4 (Web Text))

Max Activating Token Index: 69

Text #19

Max Range: 2.8898. Min Range: -2.8898

Max Act: 1.9087. Min Act: -0.0000

Data Index: 1194521 (C4 (Web Text))

Max Activating Token Index: 700