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

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

Neuron 502 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1418. Min Act: -0.0001

Data Index: 10333 (C4 (Web Text))

Max Activating Token Index: 552

Text #1

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1178. Min Act: -0.0001

Data Index: 287281 (C4 (Web Text))

Max Activating Token Index: 531

Text #2

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1122. Min Act: -0.0001

Data Index: 254717 (C4 (Web Text))

Max Activating Token Index: 926

Text #3

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1028. Min Act: -0.0001

Data Index: 261831 (C4 (Web Text))

Max Activating Token Index: 574

Text #4

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1069. Min Act: -0.0001

Data Index: 1319670 (C4 (Web Text))

Max Activating Token Index: 174

Text #5

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0947. Min Act: -0.0001

Data Index: 1276890 (C4 (Web Text))

Max Activating Token Index: 335

Text #6

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0955. Min Act: -0.0001

Data Index: 533709 (C4 (Web Text))

Max Activating Token Index: 961

Text #7

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1167782 (C4 (Web Text))

Max Activating Token Index: 865

Text #8

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1046. Min Act: -0.0001

Data Index: 1335511 (C4 (Web Text))

Max Activating Token Index: 646

Text #9

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0935. Min Act: -0.0001

Data Index: 445807 (C4 (Web Text))

Max Activating Token Index: 144

Text #10

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0923. Min Act: -0.0001

Data Index: 296731 (C4 (Web Text))

Max Activating Token Index: 758

Text #11

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0896. Min Act: -0.0001

Data Index: 64750 (C4 (Web Text))

Max Activating Token Index: 344

Text #12

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.1016. Min Act: -0.0001

Data Index: 910244 (C4 (Web Text))

Max Activating Token Index: 314

Text #13

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0907. Min Act: -0.0001

Data Index: 151795 (C4 (Web Text))

Max Activating Token Index: 286

Text #14

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0913. Min Act: -0.0001

Data Index: 714043 (C4 (Web Text))

Max Activating Token Index: 518

Text #15

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0889. Min Act: -0.0001

Data Index: 110628 (C4 (Web Text))

Max Activating Token Index: 556

Text #16

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0850. Min Act: -0.0001

Data Index: 43055 (C4 (Web Text))

Max Activating Token Index: 215

Text #17

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0864. Min Act: -0.0001

Data Index: 1098896 (C4 (Web Text))

Max Activating Token Index: 471

Text #18

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0809. Min Act: -0.0001

Data Index: 1144441 (C4 (Web Text))

Max Activating Token Index: 728

Text #19

Max Range: 0.1418. Min Range: -0.1418

Max Act: 0.0830. Min Act: -0.0001

Data Index: 560646 (C4 (Web Text))

Max Activating Token Index: 469