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

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

Neuron 3777 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.1627. Min Act: -0.0000

Data Index: 860535 (C4 (Web Text))

Max Activating Token Index: 46

Text #1

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.1119. Min Act: -0.0001

Data Index: 342665 (C4 (Web Text))

Max Activating Token Index: 225

Text #2

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.1463. Min Act: -0.0001

Data Index: 548889 (C4 (Web Text))

Max Activating Token Index: 214

Text #3

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.1031. Min Act: -0.0001

Data Index: 969540 (C4 (Web Text))

Max Activating Token Index: 720

Text #4

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.0698. Min Act: -0.0000

Data Index: 720509 (C4 (Web Text))

Max Activating Token Index: 8

Text #5

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.1822. Min Act: -0.0000

Data Index: 1067284 (C4 (Web Text))

Max Activating Token Index: 722

Text #6

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.0540. Min Act: -0.0000

Data Index: 1304526 (C4 (Web Text))

Max Activating Token Index: 6

Text #7

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.0164. Min Act: -0.0000

Data Index: 999116 (C4 (Web Text))

Max Activating Token Index: 25

Text #8

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.0443. Min Act: -0.0000

Data Index: 856041 (C4 (Web Text))

Max Activating Token Index: 70

Text #9

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9820. Min Act: -0.0000

Data Index: 584523 (C4 (Web Text))

Max Activating Token Index: 847

Text #10

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9985. Min Act: -0.0000

Data Index: 1255790 (C4 (Web Text))

Max Activating Token Index: 139

Text #11

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9848. Min Act: -0.0001

Data Index: 511001 (C4 (Web Text))

Max Activating Token Index: 866

Text #12

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9822. Min Act: -0.0000

Data Index: 789832 (C4 (Web Text))

Max Activating Token Index: 700

Text #13

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9751. Min Act: -0.0000

Data Index: 931829 (C4 (Web Text))

Max Activating Token Index: 46

Text #14

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9985. Min Act: -0.0001

Data Index: 349175 (C4 (Web Text))

Max Activating Token Index: 146

Text #15

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9679. Min Act: -0.0000

Data Index: 776386 (C4 (Web Text))

Max Activating Token Index: 8

Text #16

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.0530. Min Act: -0.0000

Data Index: 159479 (C4 (Web Text))

Max Activating Token Index: 47

Text #17

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9021. Min Act: -0.0001

Data Index: 831387 (C4 (Web Text))

Max Activating Token Index: 639

Text #18

Max Range: 1.1822. Min Range: -1.1822

Max Act: 1.0115. Min Act: -0.0000

Data Index: 300712 (C4 (Web Text))

Max Activating Token Index: 10

Text #19

Max Range: 1.1822. Min Range: -1.1822

Max Act: 0.9850. Min Act: -0.0000

Data Index: 13045 (C4 (Web Text))

Max Activating Token Index: 13