Model: SoLU Model: 3 Layers, 2048 Neurons per Layer

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

Neuron 1311 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-3l')

Text #0

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0997. Min Act: -0.0006

Data Index: 806133 (C4 (Web Text))

Max Activating Token Index: 805

Text #1

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0966. Min Act: -0.0006

Data Index: 731189 (C4 (Web Text))

Max Activating Token Index: 851

Text #2

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0925. Min Act: -0.0006

Data Index: 610073 (C4 (Web Text))

Max Activating Token Index: 760

Text #3

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0950. Min Act: -0.0006

Data Index: 688882 (C4 (Web Text))

Max Activating Token Index: 816

Text #4

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0940. Min Act: -0.0006

Data Index: 1089531 (C4 (Web Text))

Max Activating Token Index: 730

Text #5

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0936. Min Act: -0.0006

Data Index: 795099 (C4 (Web Text))

Max Activating Token Index: 28

Text #6

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0916. Min Act: -0.0006

Data Index: 1114454 (C4 (Web Text))

Max Activating Token Index: 603

Text #7

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0872. Min Act: -0.0006

Data Index: 1272388 (C4 (Web Text))

Max Activating Token Index: 925

Text #8

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0901. Min Act: -0.0006

Data Index: 1153514 (C4 (Web Text))

Max Activating Token Index: 777

Text #9

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0932. Min Act: -0.0006

Data Index: 816129 (C4 (Web Text))

Max Activating Token Index: 131

Text #10

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0918. Min Act: -0.0006

Data Index: 239314 (C4 (Web Text))

Max Activating Token Index: 277

Text #11

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0872. Min Act: -0.0006

Data Index: 634014 (C4 (Web Text))

Max Activating Token Index: 513

Text #12

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0876. Min Act: -0.0006

Data Index: 1167188 (C4 (Web Text))

Max Activating Token Index: 7

Text #13

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0868. Min Act: -0.0006

Data Index: 157202 (C4 (Web Text))

Max Activating Token Index: 254

Text #14

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0868. Min Act: -0.0006

Data Index: 681736 (C4 (Web Text))

Max Activating Token Index: 765

Text #15

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0863. Min Act: -0.0006

Data Index: 826242 (C4 (Web Text))

Max Activating Token Index: 406

Text #16

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0827. Min Act: -0.0006

Data Index: 1116610 (C4 (Web Text))

Max Activating Token Index: 951

Text #17

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0844. Min Act: -0.0006

Data Index: 91975 (C4 (Web Text))

Max Activating Token Index: 748

Text #18

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0843. Min Act: -0.0006

Data Index: 148509 (C4 (Web Text))

Max Activating Token Index: 85

Text #19

Max Range: 0.0997. Min Range: -0.0997

Max Act: 0.0839. Min Act: -0.0006

Data Index: 1284884 (C4 (Web Text))

Max Activating Token Index: 467