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

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

Neuron 1768 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.7878. Min Act: -0.0000

Data Index: 1050192 (C4 (Web Text))

Max Activating Token Index: 365

Text #1

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6809. Min Act: -0.0000

Data Index: 1057601 (C4 (Web Text))

Max Activating Token Index: 715

Text #2

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6523. Min Act: -0.0000

Data Index: 621986 (C4 (Web Text))

Max Activating Token Index: 32

Text #3

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6458. Min Act: -0.0000

Data Index: 63430 (C4 (Web Text))

Max Activating Token Index: 756

Text #4

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.6208. Min Act: -0.0000

Data Index: 1128864 (C4 (Web Text))

Max Activating Token Index: 718

Text #5

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5923. Min Act: -0.0000

Data Index: 61982 (C4 (Web Text))

Max Activating Token Index: 963

Text #6

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5631. Min Act: -0.0000

Data Index: 510325 (C4 (Web Text))

Max Activating Token Index: 732

Text #7

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5596. Min Act: -0.0000

Data Index: 1116370 (C4 (Web Text))

Max Activating Token Index: 975

Text #8

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5376. Min Act: -0.0000

Data Index: 1023577 (C4 (Web Text))

Max Activating Token Index: 586

Text #9

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4892. Min Act: -0.0000

Data Index: 900960 (C4 (Web Text))

Max Activating Token Index: 882

Text #10

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5180. Min Act: -0.0000

Data Index: 380565 (C4 (Web Text))

Max Activating Token Index: 364

Text #11

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4924. Min Act: -0.0000

Data Index: 499210 (C4 (Web Text))

Max Activating Token Index: 268

Text #12

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4889. Min Act: -0.0000

Data Index: 555613 (C4 (Web Text))

Max Activating Token Index: 68

Text #13

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5121. Min Act: -0.0000

Data Index: 1325952 (C4 (Web Text))

Max Activating Token Index: 691

Text #14

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4907. Min Act: -0.0000

Data Index: 700066 (C4 (Web Text))

Max Activating Token Index: 836

Text #15

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4865. Min Act: -0.0000

Data Index: 201144 (C4 (Web Text))

Max Activating Token Index: 582

Text #16

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4849. Min Act: -0.0000

Data Index: 129721 (C4 (Web Text))

Max Activating Token Index: 662

Text #17

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5117. Min Act: -0.0000

Data Index: 247271 (C4 (Web Text))

Max Activating Token Index: 869

Text #18

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.5149. Min Act: -0.0000

Data Index: 1352543 (C4 (Web Text))

Max Activating Token Index: 555

Text #19

Max Range: 0.7878. Min Range: -0.7878

Max Act: 0.4779. Min Act: -0.0000

Data Index: 117568 (C4 (Web Text))

Max Activating Token Index: 173