Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2970 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.6595. Min Act: -0.0001

Data Index: 399831 (C4 (Web Text))

Max Activating Token Index: 642

Text #1

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4652. Min Act: -0.0001

Data Index: 285001 (C4 (Web Text))

Max Activating Token Index: 713

Text #2

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4334. Min Act: -0.0001

Data Index: 723752 (C4 (Web Text))

Max Activating Token Index: 864

Text #3

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4937. Min Act: -0.0001

Data Index: 222899 (C4 (Web Text))

Max Activating Token Index: 366

Text #4

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4247. Min Act: -0.0001

Data Index: 62006 (C4 (Web Text))

Max Activating Token Index: 209

Text #5

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4228. Min Act: -0.0001

Data Index: 1053617 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3919. Min Act: -0.0001

Data Index: 909553 (C4 (Web Text))

Max Activating Token Index: 513

Text #7

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4092. Min Act: -0.0001

Data Index: 889757 (C4 (Web Text))

Max Activating Token Index: 120

Text #8

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4320. Min Act: -0.0001

Data Index: 1027566 (C4 (Web Text))

Max Activating Token Index: 758

Text #9

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3871. Min Act: -0.0001

Data Index: 50266 (C4 (Web Text))

Max Activating Token Index: 787

Text #10

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4127. Min Act: -0.0001

Data Index: 1087992 (C4 (Web Text))

Max Activating Token Index: 862

Text #11

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4074. Min Act: -0.0001

Data Index: 522980 (C4 (Web Text))

Max Activating Token Index: 1015

Text #12

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4196. Min Act: -0.0001

Data Index: 805220 (C4 (Web Text))

Max Activating Token Index: 978

Text #13

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.4010. Min Act: -0.0001

Data Index: 280143 (C4 (Web Text))

Max Activating Token Index: 939

Text #14

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3702. Min Act: -0.0001

Data Index: 809558 (C4 (Web Text))

Max Activating Token Index: 275

Text #15

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3941. Min Act: -0.0001

Data Index: 469025 (C4 (Web Text))

Max Activating Token Index: 10

Text #16

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3653. Min Act: -0.0001

Data Index: 760441 (C4 (Web Text))

Max Activating Token Index: 995

Text #17

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3895. Min Act: -0.0001

Data Index: 1351977 (C4 (Web Text))

Max Activating Token Index: 475

Text #18

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3785. Min Act: -0.0001

Data Index: 957706 (C4 (Web Text))

Max Activating Token Index: 109

Text #19

Max Range: 0.6595. Min Range: -0.6595

Max Act: 0.3880. Min Act: -0.0001

Data Index: 1248328 (C4 (Web Text))

Max Activating Token Index: 354