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

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

Neuron 2425 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.1007. Min Act: -0.0001

Data Index: 154666 (C4 (Web Text))

Max Activating Token Index: 180

Text #1

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0985. Min Act: -0.0001

Data Index: 225099 (C4 (Web Text))

Max Activating Token Index: 240

Text #2

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0953. Min Act: -0.0002

Data Index: 766991 (C4 (Web Text))

Max Activating Token Index: 5

Text #3

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0965. Min Act: -0.0002

Data Index: 916738 (C4 (Web Text))

Max Activating Token Index: 183

Text #4

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0840. Min Act: -0.0002

Data Index: 357840 (C4 (Web Text))

Max Activating Token Index: 257

Text #5

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0850. Min Act: -0.0001

Data Index: 606148 (C4 (Web Text))

Max Activating Token Index: 18

Text #6

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0884. Min Act: -0.0002

Data Index: 986829 (C4 (Web Text))

Max Activating Token Index: 73

Text #7

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0882. Min Act: -0.0001

Data Index: 138646 (C4 (Web Text))

Max Activating Token Index: 450

Text #8

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0888. Min Act: -0.0001

Data Index: 1179780 (C4 (Web Text))

Max Activating Token Index: 814

Text #9

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0846. Min Act: -0.0002

Data Index: 217258 (C4 (Web Text))

Max Activating Token Index: 488

Text #10

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0872. Min Act: -0.0002

Data Index: 1151268 (C4 (Web Text))

Max Activating Token Index: 137

Text #11

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0868. Min Act: -0.0002

Data Index: 1321039 (C4 (Web Text))

Max Activating Token Index: 354

Text #12

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0794. Min Act: -0.0002

Data Index: 400342 (C4 (Web Text))

Max Activating Token Index: 526

Text #13

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0776. Min Act: -0.0002

Data Index: 494304 (C4 (Web Text))

Max Activating Token Index: 252

Text #14

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0724. Min Act: -0.0001

Data Index: 712574 (C4 (Web Text))

Max Activating Token Index: 632

Text #15

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0779. Min Act: -0.0002

Data Index: 266333 (C4 (Web Text))

Max Activating Token Index: 339

Text #16

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0752. Min Act: -0.0001

Data Index: 1591646 (Python Code)

Max Activating Token Index: 959

Text #17

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0804. Min Act: -0.0001

Data Index: 296020 (C4 (Web Text))

Max Activating Token Index: 99

Text #18

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0769. Min Act: -0.0001

Data Index: 878660 (C4 (Web Text))

Max Activating Token Index: 730

Text #19

Max Range: 0.1007. Min Range: -0.1007

Max Act: 0.0759. Min Act: -0.0002

Data Index: 971222 (C4 (Web Text))

Max Activating Token Index: 716