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

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

Neuron 1967 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1021. Min Act: -0.0001

Data Index: 926839 (C4 (Web Text))

Max Activating Token Index: 27

Text #1

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.1011. Min Act: -0.0001

Data Index: 1244232 (C4 (Web Text))

Max Activating Token Index: 162

Text #2

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0931. Min Act: -0.0001

Data Index: 626371 (C4 (Web Text))

Max Activating Token Index: 84

Text #3

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0888. Min Act: -0.0001

Data Index: 354897 (C4 (Web Text))

Max Activating Token Index: 213

Text #4

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0917. Min Act: -0.0001

Data Index: 1087782 (C4 (Web Text))

Max Activating Token Index: 45

Text #5

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0825. Min Act: -0.0001

Data Index: 608989 (C4 (Web Text))

Max Activating Token Index: 750

Text #6

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0835. Min Act: -0.0001

Data Index: 847841 (C4 (Web Text))

Max Activating Token Index: 773

Text #7

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0825. Min Act: -0.0001

Data Index: 795834 (C4 (Web Text))

Max Activating Token Index: 874

Text #8

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0843. Min Act: -0.0001

Data Index: 945060 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0866. Min Act: -0.0001

Data Index: 1315507 (C4 (Web Text))

Max Activating Token Index: 920

Text #10

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0825. Min Act: -0.0001

Data Index: 46892 (C4 (Web Text))

Max Activating Token Index: 196

Text #11

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0823. Min Act: -0.0001

Data Index: 317133 (C4 (Web Text))

Max Activating Token Index: 287

Text #12

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0828. Min Act: -0.0001

Data Index: 231967 (C4 (Web Text))

Max Activating Token Index: 954

Text #13

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0844. Min Act: -0.0001

Data Index: 264335 (C4 (Web Text))

Max Activating Token Index: 572

Text #14

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0872. Min Act: -0.0001

Data Index: 544209 (C4 (Web Text))

Max Activating Token Index: 981

Text #15

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0842. Min Act: -0.0001

Data Index: 1002151 (C4 (Web Text))

Max Activating Token Index: 652

Text #16

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0727. Min Act: -0.0001

Data Index: 919722 (C4 (Web Text))

Max Activating Token Index: 113

Text #17

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0812. Min Act: -0.0001

Data Index: 1249518 (C4 (Web Text))

Max Activating Token Index: 25

Text #18

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0770. Min Act: -0.0001

Data Index: 1161420 (C4 (Web Text))

Max Activating Token Index: 751

Text #19

Max Range: 0.1021. Min Range: -0.1021

Max Act: 0.0826. Min Act: -0.0001

Data Index: 467267 (C4 (Web Text))

Max Activating Token Index: 201