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

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

Neuron 1102 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.7685. Min Act: -0.0002

Data Index: 173902 (C4 (Web Text))

Max Activating Token Index: 80

Text #1

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.9012. Min Act: -0.0002

Data Index: 727552 (C4 (Web Text))

Max Activating Token Index: 227

Text #2

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.7691. Min Act: -0.0002

Data Index: 490576 (C4 (Web Text))

Max Activating Token Index: 694

Text #3

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.6200. Min Act: -0.0002

Data Index: 1533128 (Python Code)

Max Activating Token Index: 1

Text #4

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.6200. Min Act: -0.0002

Data Index: 1460277 (Python Code)

Max Activating Token Index: 1

Text #5

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.6474. Min Act: -0.0002

Data Index: 1347129 (C4 (Web Text))

Max Activating Token Index: 78

Text #6

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5772. Min Act: -0.0002

Data Index: 692769 (C4 (Web Text))

Max Activating Token Index: 779

Text #7

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5852. Min Act: -0.0002

Data Index: 630131 (C4 (Web Text))

Max Activating Token Index: 229

Text #8

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5788. Min Act: -0.0002

Data Index: 1108215 (C4 (Web Text))

Max Activating Token Index: 789

Text #9

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5169. Min Act: -0.0002

Data Index: 370685 (C4 (Web Text))

Max Activating Token Index: 509

Text #10

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5163. Min Act: -0.0002

Data Index: 811055 (C4 (Web Text))

Max Activating Token Index: 443

Text #11

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5142. Min Act: -0.0002

Data Index: 562020 (C4 (Web Text))

Max Activating Token Index: 619

Text #12

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.5168. Min Act: -0.0002

Data Index: 499108 (C4 (Web Text))

Max Activating Token Index: 791

Text #13

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.4496. Min Act: -0.0002

Data Index: 862460 (C4 (Web Text))

Max Activating Token Index: 614

Text #14

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.3261. Min Act: -0.0002

Data Index: 763315 (C4 (Web Text))

Max Activating Token Index: 732

Text #15

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.3886. Min Act: -0.0002

Data Index: 1476960 (Python Code)

Max Activating Token Index: 4

Text #16

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.3863. Min Act: -0.0002

Data Index: 515189 (C4 (Web Text))

Max Activating Token Index: 715

Text #17

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.4509. Min Act: -0.0002

Data Index: 287124 (C4 (Web Text))

Max Activating Token Index: 96

Text #18

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.3813. Min Act: -0.0002

Data Index: 944077 (C4 (Web Text))

Max Activating Token Index: 736

Text #19

Max Range: 14.9012. Min Range: -14.9012

Max Act: 14.3268. Min Act: -0.0002

Data Index: 1287361 (C4 (Web Text))

Max Activating Token Index: 356