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

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

Neuron 1906 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: 2.5836. Min Range: -2.5836

Max Act: 2.5836. Min Act: -0.0000

Data Index: 1360659 (Python Code)

Max Activating Token Index: 205

Text #1

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.3739. Min Act: -0.0000

Data Index: 37827 (C4 (Web Text))

Max Activating Token Index: 314

Text #2

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.4560. Min Act: -0.0000

Data Index: 494546 (C4 (Web Text))

Max Activating Token Index: 883

Text #3

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.3476. Min Act: -0.0000

Data Index: 533895 (C4 (Web Text))

Max Activating Token Index: 642

Text #4

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.2889. Min Act: -0.0000

Data Index: 575355 (C4 (Web Text))

Max Activating Token Index: 322

Text #5

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.2567. Min Act: -0.0000

Data Index: 178199 (C4 (Web Text))

Max Activating Token Index: 233

Text #6

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.2569. Min Act: -0.0000

Data Index: 1170457 (C4 (Web Text))

Max Activating Token Index: 868

Text #7

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.1651. Min Act: -0.0000

Data Index: 1328829 (C4 (Web Text))

Max Activating Token Index: 18

Text #8

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.0466. Min Act: -0.0000

Data Index: 1201606 (C4 (Web Text))

Max Activating Token Index: 505

Text #9

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.1485. Min Act: -0.0000

Data Index: 1008520 (C4 (Web Text))

Max Activating Token Index: 954

Text #10

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.0753. Min Act: -0.0000

Data Index: 13604 (C4 (Web Text))

Max Activating Token Index: 739

Text #11

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.0685. Min Act: -0.0000

Data Index: 298011 (C4 (Web Text))

Max Activating Token Index: 42

Text #12

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.1819. Min Act: -0.0000

Data Index: 377207 (C4 (Web Text))

Max Activating Token Index: 999

Text #13

Max Range: 2.5836. Min Range: -2.5836

Max Act: 1.9279. Min Act: -0.0000

Data Index: 112514 (C4 (Web Text))

Max Activating Token Index: 996

Text #14

Max Range: 2.5836. Min Range: -2.5836

Max Act: 1.9258. Min Act: -0.0000

Data Index: 1315936 (C4 (Web Text))

Max Activating Token Index: 352

Text #15

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.0365. Min Act: -0.0000

Data Index: 1116822 (C4 (Web Text))

Max Activating Token Index: 696

Text #16

Max Range: 2.5836. Min Range: -2.5836

Max Act: 2.0057. Min Act: -0.0000

Data Index: 1083071 (C4 (Web Text))

Max Activating Token Index: 12

Text #17

Max Range: 2.5836. Min Range: -2.5836

Max Act: 1.9973. Min Act: -0.0000

Data Index: 1249159 (C4 (Web Text))

Max Activating Token Index: 307

Text #18

Max Range: 2.5836. Min Range: -2.5836

Max Act: 1.9824. Min Act: -0.0000

Data Index: 1158626 (C4 (Web Text))

Max Activating Token Index: 252

Text #19

Max Range: 2.5836. Min Range: -2.5836

Max Act: 1.9697. Min Act: -0.0000

Data Index: 1187570 (C4 (Web Text))

Max Activating Token Index: 328