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

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

Neuron 1049 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.0805. Min Range: -1.0805

Max Act: 1.0805. Min Act: -0.0000

Data Index: 86336 (C4 (Web Text))

Max Activating Token Index: 522

Text #1

Max Range: 1.0805. Min Range: -1.0805

Max Act: 1.0754. Min Act: -0.0000

Data Index: 532799 (C4 (Web Text))

Max Activating Token Index: 307

Text #2

Max Range: 1.0805. Min Range: -1.0805

Max Act: 1.0584. Min Act: -0.0000

Data Index: 889424 (C4 (Web Text))

Max Activating Token Index: 321

Text #3

Max Range: 1.0805. Min Range: -1.0805

Max Act: 1.0584. Min Act: -0.0000

Data Index: 1322377 (C4 (Web Text))

Max Activating Token Index: 612

Text #4

Max Range: 1.0805. Min Range: -1.0805

Max Act: 1.0391. Min Act: -0.0000

Data Index: 32880 (C4 (Web Text))

Max Activating Token Index: 513

Text #5

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9904. Min Act: -0.0000

Data Index: 1209757 (C4 (Web Text))

Max Activating Token Index: 322

Text #6

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9634. Min Act: -0.0000

Data Index: 933487 (C4 (Web Text))

Max Activating Token Index: 866

Text #7

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9399. Min Act: -0.0000

Data Index: 232580 (C4 (Web Text))

Max Activating Token Index: 199

Text #8

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9527. Min Act: -0.0000

Data Index: 1249899 (C4 (Web Text))

Max Activating Token Index: 177

Text #9

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9827. Min Act: -0.0000

Data Index: 1304068 (C4 (Web Text))

Max Activating Token Index: 622

Text #10

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9465. Min Act: -0.0000

Data Index: 268920 (C4 (Web Text))

Max Activating Token Index: 824

Text #11

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9263. Min Act: -0.0000

Data Index: 1028648 (C4 (Web Text))

Max Activating Token Index: 673

Text #12

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8775. Min Act: -0.0000

Data Index: 1130199 (C4 (Web Text))

Max Activating Token Index: 830

Text #13

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8973. Min Act: -0.0000

Data Index: 600954 (C4 (Web Text))

Max Activating Token Index: 582

Text #14

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8747. Min Act: -0.0000

Data Index: 9496 (C4 (Web Text))

Max Activating Token Index: 618

Text #15

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8828. Min Act: -0.0000

Data Index: 72059 (C4 (Web Text))

Max Activating Token Index: 377

Text #16

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8824. Min Act: -0.0000

Data Index: 867555 (C4 (Web Text))

Max Activating Token Index: 286

Text #17

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.9040. Min Act: -0.0000

Data Index: 824345 (C4 (Web Text))

Max Activating Token Index: 1011

Text #18

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8762. Min Act: -0.0000

Data Index: 590406 (C4 (Web Text))

Max Activating Token Index: 683

Text #19

Max Range: 1.0805. Min Range: -1.0805

Max Act: 0.8808. Min Act: -0.0000

Data Index: 554102 (C4 (Web Text))

Max Activating Token Index: 92