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

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

Neuron 2103 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0955. Min Act: -0.0001

Data Index: 131113 (C4 (Web Text))

Max Activating Token Index: 244

Text #1

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0935. Min Act: -0.0001

Data Index: 1217347 (C4 (Web Text))

Max Activating Token Index: 332

Text #2

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0909. Min Act: -0.0001

Data Index: 1221464 (C4 (Web Text))

Max Activating Token Index: 361

Text #3

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0878. Min Act: -0.0001

Data Index: 737439 (C4 (Web Text))

Max Activating Token Index: 23

Text #4

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0898. Min Act: -0.0001

Data Index: 470569 (C4 (Web Text))

Max Activating Token Index: 345

Text #5

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0817. Min Act: -0.0001

Data Index: 588677 (C4 (Web Text))

Max Activating Token Index: 197

Text #6

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0869. Min Act: -0.0001

Data Index: 1631701 (Python Code)

Max Activating Token Index: 91

Text #7

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0870. Min Act: -0.0001

Data Index: 1580922 (Python Code)

Max Activating Token Index: 625

Text #8

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0856. Min Act: -0.0001

Data Index: 1006779 (C4 (Web Text))

Max Activating Token Index: 360

Text #9

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0790. Min Act: -0.0001

Data Index: 96535 (C4 (Web Text))

Max Activating Token Index: 63

Text #10

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0783. Min Act: -0.0001

Data Index: 886127 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0854. Min Act: -0.0001

Data Index: 755125 (C4 (Web Text))

Max Activating Token Index: 667

Text #12

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0804. Min Act: -0.0001

Data Index: 1130261 (C4 (Web Text))

Max Activating Token Index: 290

Text #13

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0839. Min Act: -0.0001

Data Index: 795120 (C4 (Web Text))

Max Activating Token Index: 604

Text #14

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0774. Min Act: -0.0001

Data Index: 50466 (C4 (Web Text))

Max Activating Token Index: 36

Text #15

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1481963 (Python Code)

Max Activating Token Index: 441

Text #16

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0823. Min Act: -0.0001

Data Index: 844949 (C4 (Web Text))

Max Activating Token Index: 619

Text #17

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0725. Min Act: -0.0001

Data Index: 387395 (C4 (Web Text))

Max Activating Token Index: 549

Text #18

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0782. Min Act: -0.0001

Data Index: 1154776 (C4 (Web Text))

Max Activating Token Index: 57

Text #19

Max Range: 0.0955. Min Range: -0.0955

Max Act: 0.0907. Min Act: -0.0001

Data Index: 191886 (C4 (Web Text))

Max Activating Token Index: 262