Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1608 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0848. Min Act: -0.0002

Data Index: 131415 (C4 (Web Text))

Max Activating Token Index: 533

Text #1

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0834. Min Act: -0.0002

Data Index: 1123012 (C4 (Web Text))

Max Activating Token Index: 520

Text #2

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0815. Min Act: -0.0002

Data Index: 143786 (C4 (Web Text))

Max Activating Token Index: 136

Text #3

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0795. Min Act: -0.0002

Data Index: 799293 (C4 (Web Text))

Max Activating Token Index: 336

Text #4

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0783. Min Act: -0.0002

Data Index: 289239 (C4 (Web Text))

Max Activating Token Index: 521

Text #5

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0784. Min Act: -0.0002

Data Index: 1067027 (C4 (Web Text))

Max Activating Token Index: 102

Text #6

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0773. Min Act: -0.0002

Data Index: 30041 (C4 (Web Text))

Max Activating Token Index: 565

Text #7

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0769. Min Act: -0.0002

Data Index: 190088 (C4 (Web Text))

Max Activating Token Index: 136

Text #8

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0764. Min Act: -0.0002

Data Index: 1061520 (C4 (Web Text))

Max Activating Token Index: 426

Text #9

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0751. Min Act: -0.0002

Data Index: 481518 (C4 (Web Text))

Max Activating Token Index: 236

Text #10

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0763. Min Act: -0.0002

Data Index: 787788 (C4 (Web Text))

Max Activating Token Index: 361

Text #11

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0751. Min Act: -0.0002

Data Index: 409194 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0758. Min Act: -0.0002

Data Index: 1086399 (C4 (Web Text))

Max Activating Token Index: 125

Text #13

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0748. Min Act: -0.0002

Data Index: 217656 (C4 (Web Text))

Max Activating Token Index: 122

Text #14

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0759. Min Act: -0.0002

Data Index: 20010 (C4 (Web Text))

Max Activating Token Index: 74

Text #15

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0754. Min Act: -0.0002

Data Index: 814350 (C4 (Web Text))

Max Activating Token Index: 544

Text #16

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1303361 (C4 (Web Text))

Max Activating Token Index: 622

Text #17

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0722. Min Act: -0.0002

Data Index: 76635 (C4 (Web Text))

Max Activating Token Index: 715

Text #18

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0735. Min Act: -0.0002

Data Index: 529521 (C4 (Web Text))

Max Activating Token Index: 582

Text #19

Max Range: 0.0848. Min Range: -0.0848

Max Act: 0.0738. Min Act: -0.0002

Data Index: 1144651 (C4 (Web Text))

Max Activating Token Index: 215