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

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

Neuron 1911 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: 0.1112. Min Range: -0.1112

Max Act: 0.1112. Min Act: -0.0002

Data Index: 722405 (C4 (Web Text))

Max Activating Token Index: 627

Text #1

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1040. Min Act: -0.0002

Data Index: 439379 (C4 (Web Text))

Max Activating Token Index: 877

Text #2

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1096. Min Act: -0.0002

Data Index: 1157889 (C4 (Web Text))

Max Activating Token Index: 778

Text #3

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1087. Min Act: -0.0002

Data Index: 1182524 (C4 (Web Text))

Max Activating Token Index: 984

Text #4

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1026. Min Act: -0.0002

Data Index: 83380 (C4 (Web Text))

Max Activating Token Index: 578

Text #5

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1062. Min Act: -0.0002

Data Index: 794104 (C4 (Web Text))

Max Activating Token Index: 103

Text #6

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1011. Min Act: -0.0002

Data Index: 923351 (C4 (Web Text))

Max Activating Token Index: 907

Text #7

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1012. Min Act: -0.0002

Data Index: 429333 (C4 (Web Text))

Max Activating Token Index: 135

Text #8

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1016. Min Act: -0.0002

Data Index: 386776 (C4 (Web Text))

Max Activating Token Index: 637

Text #9

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.1065. Min Act: -0.0002

Data Index: 1001708 (C4 (Web Text))

Max Activating Token Index: 909

Text #10

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0984. Min Act: -0.0002

Data Index: 944882 (C4 (Web Text))

Max Activating Token Index: 304

Text #11

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0983. Min Act: -0.0002

Data Index: 552454 (C4 (Web Text))

Max Activating Token Index: 610

Text #12

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0939. Min Act: -0.0002

Data Index: 798218 (C4 (Web Text))

Max Activating Token Index: 992

Text #13

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0938. Min Act: -0.0002

Data Index: 218485 (C4 (Web Text))

Max Activating Token Index: 965

Text #14

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0978. Min Act: -0.0002

Data Index: 250094 (C4 (Web Text))

Max Activating Token Index: 831

Text #15

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0993. Min Act: -0.0002

Data Index: 1348878 (C4 (Web Text))

Max Activating Token Index: 549

Text #16

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0995. Min Act: -0.0002

Data Index: 1121511 (C4 (Web Text))

Max Activating Token Index: 561

Text #17

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0910. Min Act: -0.0002

Data Index: 731205 (C4 (Web Text))

Max Activating Token Index: 383

Text #18

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0970. Min Act: -0.0002

Data Index: 148175 (C4 (Web Text))

Max Activating Token Index: 630

Text #19

Max Range: 0.1112. Min Range: -0.1112

Max Act: 0.0911. Min Act: -0.0002

Data Index: 513612 (C4 (Web Text))

Max Activating Token Index: 614