Model: SoLU Model: 10 Layers, 5120 Neurons per Layer

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

Neuron 3683 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l')

Text #0

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1323133 (C4 (Web Text))

Max Activating Token Index: 129

Text #1

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0905. Min Act: -0.0000

Data Index: 66935 (C4 (Web Text))

Max Activating Token Index: 693

Text #2

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1030. Min Act: -0.0000

Data Index: 1220110 (C4 (Web Text))

Max Activating Token Index: 730

Text #3

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.1004. Min Act: -0.0000

Data Index: 1250693 (C4 (Web Text))

Max Activating Token Index: 223

Text #4

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0922. Min Act: -0.0000

Data Index: 37959 (C4 (Web Text))

Max Activating Token Index: 682

Text #5

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0838. Min Act: -0.0000

Data Index: 1258040 (C4 (Web Text))

Max Activating Token Index: 863

Text #6

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0820. Min Act: -0.0000

Data Index: 1110732 (C4 (Web Text))

Max Activating Token Index: 722

Text #7

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0825. Min Act: -0.0000

Data Index: 350069 (C4 (Web Text))

Max Activating Token Index: 993

Text #8

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0771. Min Act: -0.0000

Data Index: 1277066 (C4 (Web Text))

Max Activating Token Index: 675

Text #9

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0734. Min Act: -0.0000

Data Index: 953697 (C4 (Web Text))

Max Activating Token Index: 62

Text #10

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0766. Min Act: -0.0000

Data Index: 215580 (C4 (Web Text))

Max Activating Token Index: 616

Text #11

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0685. Min Act: -0.0000

Data Index: 636561 (C4 (Web Text))

Max Activating Token Index: 722

Text #12

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0737. Min Act: -0.0000

Data Index: 431720 (C4 (Web Text))

Max Activating Token Index: 489

Text #13

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0729. Min Act: -0.0000

Data Index: 249432 (C4 (Web Text))

Max Activating Token Index: 26

Text #14

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0716. Min Act: -0.0000

Data Index: 872487 (C4 (Web Text))

Max Activating Token Index: 920

Text #15

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0761. Min Act: -0.0000

Data Index: 471693 (C4 (Web Text))

Max Activating Token Index: 283

Text #16

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0727. Min Act: -0.0000

Data Index: 1091246 (C4 (Web Text))

Max Activating Token Index: 613

Text #17

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0724. Min Act: -0.0000

Data Index: 31758 (C4 (Web Text))

Max Activating Token Index: 128

Text #18

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0690. Min Act: -0.0000

Data Index: 557531 (C4 (Web Text))

Max Activating Token Index: 932

Text #19

Max Range: 0.1030. Min Range: -0.1030

Max Act: 0.0694. Min Act: -0.0000

Data Index: 935150 (C4 (Web Text))

Max Activating Token Index: 525