Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

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

Neuron 2439 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l')

Text #0

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0876. Min Act: -0.0000

Data Index: 872826 (C4 (Web Text))

Max Activating Token Index: 185

Text #1

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0817. Min Act: -0.0000

Data Index: 313088 (C4 (Web Text))

Max Activating Token Index: 982

Text #2

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0845. Min Act: -0.0001

Data Index: 556347 (C4 (Web Text))

Max Activating Token Index: 796

Text #3

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0748. Min Act: -0.0001

Data Index: 195278 (C4 (Web Text))

Max Activating Token Index: 371

Text #4

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0777. Min Act: -0.0001

Data Index: 128941 (C4 (Web Text))

Max Activating Token Index: 782

Text #5

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0676. Min Act: -0.0000

Data Index: 1305950 (C4 (Web Text))

Max Activating Token Index: 953

Text #6

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0723. Min Act: -0.0001

Data Index: 854879 (C4 (Web Text))

Max Activating Token Index: 753

Text #7

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0751. Min Act: -0.0000

Data Index: 1078656 (C4 (Web Text))

Max Activating Token Index: 610

Text #8

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0701. Min Act: -0.0001

Data Index: 563806 (C4 (Web Text))

Max Activating Token Index: 688

Text #9

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0742. Min Act: -0.0001

Data Index: 1422893 (Python Code)

Max Activating Token Index: 504

Text #10

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0766. Min Act: -0.0001

Data Index: 502154 (C4 (Web Text))

Max Activating Token Index: 105

Text #11

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0765. Min Act: -0.0000

Data Index: 110069 (C4 (Web Text))

Max Activating Token Index: 990

Text #12

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0736. Min Act: -0.0000

Data Index: 1466247 (Python Code)

Max Activating Token Index: 997

Text #13

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0616. Min Act: -0.0001

Data Index: 1103253 (C4 (Web Text))

Max Activating Token Index: 869

Text #14

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0714. Min Act: -0.0001

Data Index: 120026 (C4 (Web Text))

Max Activating Token Index: 96

Text #15

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0708. Min Act: -0.0000

Data Index: 773880 (C4 (Web Text))

Max Activating Token Index: 154

Text #16

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0704. Min Act: -0.0000

Data Index: 412062 (C4 (Web Text))

Max Activating Token Index: 803

Text #17

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0733. Min Act: -0.0001

Data Index: 1230911 (C4 (Web Text))

Max Activating Token Index: 844

Text #18

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0684. Min Act: -0.0001

Data Index: 755746 (C4 (Web Text))

Max Activating Token Index: 364

Text #19

Max Range: 0.0876. Min Range: -0.0876

Max Act: 0.0668. Min Act: -0.0000

Data Index: 1052849 (C4 (Web Text))

Max Activating Token Index: 93