Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

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

Neuron 39 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l')

Text #0

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0856. Min Act: -0.0003

Data Index: 464267 (C4 (Web Text))

Max Activating Token Index: 651

Text #1

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0706. Min Act: -0.0003

Data Index: 531173 (C4 (Web Text))

Max Activating Token Index: 668

Text #2

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0867. Min Act: -0.0003

Data Index: 261359 (C4 (Web Text))

Max Activating Token Index: 605

Text #3

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0801. Min Act: -0.0003

Data Index: 284896 (C4 (Web Text))

Max Activating Token Index: 296

Text #4

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0772. Min Act: -0.0003

Data Index: 366286 (C4 (Web Text))

Max Activating Token Index: 156

Text #5

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0809. Min Act: -0.0003

Data Index: 938245 (C4 (Web Text))

Max Activating Token Index: 886

Text #6

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0706. Min Act: -0.0003

Data Index: 937822 (C4 (Web Text))

Max Activating Token Index: 890

Text #7

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0737. Min Act: -0.0003

Data Index: 751195 (C4 (Web Text))

Max Activating Token Index: 844

Text #8

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0689. Min Act: -0.0003

Data Index: 477156 (C4 (Web Text))

Max Activating Token Index: 839

Text #9

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0684. Min Act: -0.0003

Data Index: 1128625 (C4 (Web Text))

Max Activating Token Index: 862

Text #10

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0651. Min Act: -0.0003

Data Index: 692403 (C4 (Web Text))

Max Activating Token Index: 668

Text #11

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0719. Min Act: -0.0003

Data Index: 1074474 (C4 (Web Text))

Max Activating Token Index: 757

Text #12

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0712. Min Act: -0.0003

Data Index: 847165 (C4 (Web Text))

Max Activating Token Index: 976

Text #13

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0712. Min Act: -0.0003

Data Index: 1005664 (C4 (Web Text))

Max Activating Token Index: 829

Text #14

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0609. Min Act: -0.0003

Data Index: 1076476 (C4 (Web Text))

Max Activating Token Index: 922

Text #15

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0678. Min Act: -0.0003

Data Index: 369282 (C4 (Web Text))

Max Activating Token Index: 760

Text #16

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0710. Min Act: -0.0003

Data Index: 619897 (C4 (Web Text))

Max Activating Token Index: 680

Text #17

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0608. Min Act: -0.0003

Data Index: 169083 (C4 (Web Text))

Max Activating Token Index: 867

Text #18

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0697. Min Act: -0.0003

Data Index: 1140154 (C4 (Web Text))

Max Activating Token Index: 1009

Text #19

Max Range: 0.0867. Min Range: -0.0867

Max Act: 0.0696. Min Act: -0.0003

Data Index: 926059 (C4 (Web Text))

Max Activating Token Index: 565