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

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

Neuron 1040 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: 10.6755. Min Range: -10.6755

Max Act: 10.6755. Min Act: -0.0000

Data Index: 837225 (C4 (Web Text))

Max Activating Token Index: 76

Text #1

Max Range: 10.6755. Min Range: -10.6755

Max Act: 9.5456. Min Act: -0.0000

Data Index: 1016577 (C4 (Web Text))

Max Activating Token Index: 76

Text #2

Max Range: 10.6755. Min Range: -10.6755

Max Act: 9.3796. Min Act: -0.0000

Data Index: 1156295 (C4 (Web Text))

Max Activating Token Index: 8

Text #3

Max Range: 10.6755. Min Range: -10.6755

Max Act: 9.4998. Min Act: -0.0000

Data Index: 1038763 (C4 (Web Text))

Max Activating Token Index: 853

Text #4

Max Range: 10.6755. Min Range: -10.6755

Max Act: 9.3356. Min Act: -0.0000

Data Index: 913770 (C4 (Web Text))

Max Activating Token Index: 182

Text #5

Max Range: 10.6755. Min Range: -10.6755

Max Act: 9.2643. Min Act: -0.0000

Data Index: 231375 (C4 (Web Text))

Max Activating Token Index: 47

Text #6

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.9996. Min Act: -0.0000

Data Index: 193207 (C4 (Web Text))

Max Activating Token Index: 167

Text #7

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.9726. Min Act: -0.0000

Data Index: 1153847 (C4 (Web Text))

Max Activating Token Index: 839

Text #8

Max Range: 10.6755. Min Range: -10.6755

Max Act: 9.0285. Min Act: -0.0000

Data Index: 311215 (C4 (Web Text))

Max Activating Token Index: 87

Text #9

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.8842. Min Act: -0.0000

Data Index: 788000 (C4 (Web Text))

Max Activating Token Index: 66

Text #10

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.8782. Min Act: -0.0000

Data Index: 1100661 (C4 (Web Text))

Max Activating Token Index: 101

Text #11

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.8392. Min Act: -0.0001

Data Index: 1211868 (C4 (Web Text))

Max Activating Token Index: 37

Text #12

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.6489. Min Act: -0.0000

Data Index: 625697 (C4 (Web Text))

Max Activating Token Index: 71

Text #13

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.7668. Min Act: -0.0000

Data Index: 466949 (C4 (Web Text))

Max Activating Token Index: 12

Text #14

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.5758. Min Act: -0.0000

Data Index: 196994 (C4 (Web Text))

Max Activating Token Index: 78

Text #15

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.8626. Min Act: -0.0000

Data Index: 1117810 (C4 (Web Text))

Max Activating Token Index: 20

Text #16

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.8420. Min Act: -0.0000

Data Index: 1197604 (C4 (Web Text))

Max Activating Token Index: 722

Text #17

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.5343. Min Act: -0.0000

Data Index: 762815 (C4 (Web Text))

Max Activating Token Index: 116

Text #18

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.5004. Min Act: -0.0000

Data Index: 751372 (C4 (Web Text))

Max Activating Token Index: 28

Text #19

Max Range: 10.6755. Min Range: -10.6755

Max Act: 8.4914. Min Act: -0.0000

Data Index: 357738 (C4 (Web Text))

Max Activating Token Index: 257