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

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

Neuron 1917 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5250. Min Act: -0.0001

Data Index: 840422 (C4 (Web Text))

Max Activating Token Index: 840

Text #1

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5597. Min Act: -0.0001

Data Index: 92895 (C4 (Web Text))

Max Activating Token Index: 945

Text #2

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5354. Min Act: -0.0001

Data Index: 206754 (C4 (Web Text))

Max Activating Token Index: 866

Text #3

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5400. Min Act: -0.0001

Data Index: 909758 (C4 (Web Text))

Max Activating Token Index: 905

Text #4

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5644. Min Act: -0.0001

Data Index: 172738 (C4 (Web Text))

Max Activating Token Index: 825

Text #5

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4899. Min Act: -0.0001

Data Index: 590098 (C4 (Web Text))

Max Activating Token Index: 545

Text #6

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5222. Min Act: -0.0001

Data Index: 16391 (C4 (Web Text))

Max Activating Token Index: 893

Text #7

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5580. Min Act: -0.0001

Data Index: 1283715 (C4 (Web Text))

Max Activating Token Index: 872

Text #8

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5378. Min Act: -0.0000

Data Index: 194030 (C4 (Web Text))

Max Activating Token Index: 869

Text #9

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5214. Min Act: -0.0000

Data Index: 1487986 (Python Code)

Max Activating Token Index: 119

Text #10

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5398. Min Act: -0.0001

Data Index: 747162 (C4 (Web Text))

Max Activating Token Index: 552

Text #11

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5294. Min Act: -0.0001

Data Index: 813552 (C4 (Web Text))

Max Activating Token Index: 671

Text #12

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5294. Min Act: -0.0000

Data Index: 510366 (C4 (Web Text))

Max Activating Token Index: 475

Text #13

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5287. Min Act: -0.0000

Data Index: 948964 (C4 (Web Text))

Max Activating Token Index: 78

Text #14

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5294. Min Act: -0.0001

Data Index: 1077569 (C4 (Web Text))

Max Activating Token Index: 750

Text #15

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5251. Min Act: -0.0001

Data Index: 1136232 (C4 (Web Text))

Max Activating Token Index: 740

Text #16

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5406. Min Act: -0.0001

Data Index: 787194 (C4 (Web Text))

Max Activating Token Index: 837

Text #17

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4718. Min Act: -0.0000

Data Index: 1267215 (C4 (Web Text))

Max Activating Token Index: 680

Text #18

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.5201. Min Act: -0.0000

Data Index: 1551400 (Python Code)

Max Activating Token Index: 54

Text #19

Max Range: 0.5644. Min Range: -0.5644

Max Act: 0.4968. Min Act: -0.0000

Data Index: 907407 (C4 (Web Text))

Max Activating Token Index: 213