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

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

Neuron 2433 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0972. Min Act: -0.0001

Data Index: 471366 (C4 (Web Text))

Max Activating Token Index: 269

Text #1

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0001

Data Index: 416550 (C4 (Web Text))

Max Activating Token Index: 892

Text #2

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0886. Min Act: -0.0001

Data Index: 377734 (C4 (Web Text))

Max Activating Token Index: 128

Text #3

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0947. Min Act: -0.0001

Data Index: 342957 (C4 (Web Text))

Max Activating Token Index: 53

Text #4

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0927. Min Act: -0.0001

Data Index: 75295 (C4 (Web Text))

Max Activating Token Index: 892

Text #5

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0937. Min Act: -0.0001

Data Index: 611270 (C4 (Web Text))

Max Activating Token Index: 643

Text #6

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0991. Min Act: -0.0001

Data Index: 578930 (C4 (Web Text))

Max Activating Token Index: 632

Text #7

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0962. Min Act: -0.0001

Data Index: 1180344 (C4 (Web Text))

Max Activating Token Index: 825

Text #8

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0875. Min Act: -0.0001

Data Index: 154965 (C4 (Web Text))

Max Activating Token Index: 147

Text #9

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0855. Min Act: -0.0001

Data Index: 1343906 (C4 (Web Text))

Max Activating Token Index: 747

Text #10

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0905. Min Act: -0.0001

Data Index: 1194827 (C4 (Web Text))

Max Activating Token Index: 786

Text #11

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0829. Min Act: -0.0001

Data Index: 1205102 (C4 (Web Text))

Max Activating Token Index: 162

Text #12

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0799. Min Act: -0.0001

Data Index: 611168 (C4 (Web Text))

Max Activating Token Index: 869

Text #13

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0764. Min Act: -0.0001

Data Index: 793687 (C4 (Web Text))

Max Activating Token Index: 95

Text #14

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0718. Min Act: -0.0001

Data Index: 1645310 (Python Code)

Max Activating Token Index: 104

Text #15

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0769. Min Act: -0.0001

Data Index: 538879 (C4 (Web Text))

Max Activating Token Index: 826

Text #16

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0721. Min Act: -0.0001

Data Index: 194806 (C4 (Web Text))

Max Activating Token Index: 853

Text #17

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0698. Min Act: -0.0001

Data Index: 412316 (C4 (Web Text))

Max Activating Token Index: 69

Text #18

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0670. Min Act: -0.0001

Data Index: 1332057 (C4 (Web Text))

Max Activating Token Index: 966

Text #19

Max Range: 0.0991. Min Range: -0.0991

Max Act: 0.0688. Min Act: -0.0001

Data Index: 987328 (C4 (Web Text))

Max Activating Token Index: 557