Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 1770 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1096. Min Act: -0.0001

Data Index: 257830 (C4 (Web Text))

Max Activating Token Index: 984

Text #1

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.1091. Min Act: -0.0001

Data Index: 1153531 (C4 (Web Text))

Max Activating Token Index: 946

Text #2

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0959. Min Act: -0.0001

Data Index: 574130 (C4 (Web Text))

Max Activating Token Index: 691

Text #3

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0948. Min Act: -0.0001

Data Index: 137657 (C4 (Web Text))

Max Activating Token Index: 208

Text #4

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0866. Min Act: -0.0001

Data Index: 840894 (C4 (Web Text))

Max Activating Token Index: 376

Text #5

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0949. Min Act: -0.0001

Data Index: 422920 (C4 (Web Text))

Max Activating Token Index: 134

Text #6

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0912. Min Act: -0.0001

Data Index: 1234560 (C4 (Web Text))

Max Activating Token Index: 85

Text #7

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0862. Min Act: -0.0001

Data Index: 433456 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0861. Min Act: -0.0001

Data Index: 674754 (C4 (Web Text))

Max Activating Token Index: 422

Text #9

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0813. Min Act: -0.0001

Data Index: 1022468 (C4 (Web Text))

Max Activating Token Index: 885

Text #10

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0856. Min Act: -0.0001

Data Index: 335635 (C4 (Web Text))

Max Activating Token Index: 38

Text #11

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0858. Min Act: -0.0001

Data Index: 256382 (C4 (Web Text))

Max Activating Token Index: 792

Text #12

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0852. Min Act: -0.0001

Data Index: 476466 (C4 (Web Text))

Max Activating Token Index: 868

Text #13

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0851. Min Act: -0.0001

Data Index: 434260 (C4 (Web Text))

Max Activating Token Index: 30

Text #14

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0895. Min Act: -0.0001

Data Index: 744046 (C4 (Web Text))

Max Activating Token Index: 885

Text #15

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0788. Min Act: -0.0001

Data Index: 26631 (C4 (Web Text))

Max Activating Token Index: 830

Text #16

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0822. Min Act: -0.0001

Data Index: 1096699 (C4 (Web Text))

Max Activating Token Index: 908

Text #17

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0828. Min Act: -0.0001

Data Index: 659143 (C4 (Web Text))

Max Activating Token Index: 39

Text #18

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0783. Min Act: -0.0001

Data Index: 275035 (C4 (Web Text))

Max Activating Token Index: 127

Text #19

Max Range: 0.1096. Min Range: -0.1096

Max Act: 0.0833. Min Act: -0.0001

Data Index: 743842 (C4 (Web Text))

Max Activating Token Index: 930