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

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

Neuron 462 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1366528 (Python Code)

Max Activating Token Index: 860

Text #1

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0898. Min Act: -0.0000

Data Index: 351569 (C4 (Web Text))

Max Activating Token Index: 708

Text #2

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0714. Min Act: -0.0000

Data Index: 1195166 (C4 (Web Text))

Max Activating Token Index: 24

Text #3

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0705. Min Act: -0.0000

Data Index: 619279 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0682. Min Act: -0.0000

Data Index: 871755 (C4 (Web Text))

Max Activating Token Index: 164

Text #5

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0642. Min Act: -0.0000

Data Index: 1500307 (Python Code)

Max Activating Token Index: 339

Text #6

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0663. Min Act: -0.0000

Data Index: 1413024 (Python Code)

Max Activating Token Index: 691

Text #7

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0639. Min Act: -0.0000

Data Index: 525880 (C4 (Web Text))

Max Activating Token Index: 171

Text #8

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0665. Min Act: -0.0000

Data Index: 1158154 (C4 (Web Text))

Max Activating Token Index: 529

Text #9

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0702. Min Act: -0.0000

Data Index: 79152 (C4 (Web Text))

Max Activating Token Index: 125

Text #10

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0632. Min Act: -0.0000

Data Index: 1062058 (C4 (Web Text))

Max Activating Token Index: 113

Text #11

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0654. Min Act: -0.0000

Data Index: 323045 (C4 (Web Text))

Max Activating Token Index: 70

Text #12

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0674. Min Act: -0.0000

Data Index: 598624 (C4 (Web Text))

Max Activating Token Index: 205

Text #13

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0649. Min Act: -0.0000

Data Index: 713898 (C4 (Web Text))

Max Activating Token Index: 48

Text #14

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0629. Min Act: -0.0000

Data Index: 467580 (C4 (Web Text))

Max Activating Token Index: 204

Text #15

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0627. Min Act: -0.0000

Data Index: 354450 (C4 (Web Text))

Max Activating Token Index: 62

Text #16

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0623. Min Act: -0.0000

Data Index: 36767 (C4 (Web Text))

Max Activating Token Index: 145

Text #17

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0577. Min Act: -0.0000

Data Index: 43232 (C4 (Web Text))

Max Activating Token Index: 334

Text #18

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0638. Min Act: -0.0000

Data Index: 1126155 (C4 (Web Text))

Max Activating Token Index: 137

Text #19

Max Range: 0.0898. Min Range: -0.0898

Max Act: 0.0590. Min Act: -0.0000

Data Index: 1105912 (C4 (Web Text))

Max Activating Token Index: 512