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

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

Neuron 2612 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.9414. Min Act: -0.0000

Data Index: 425861 (C4 (Web Text))

Max Activating Token Index: 11

Text #1

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.5950. Min Act: -0.0000

Data Index: 654859 (C4 (Web Text))

Max Activating Token Index: 453

Text #2

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.6007. Min Act: -0.0000

Data Index: 875601 (C4 (Web Text))

Max Activating Token Index: 567

Text #3

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.7020. Min Act: -0.0000

Data Index: 1143269 (C4 (Web Text))

Max Activating Token Index: 263

Text #4

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.5915. Min Act: -0.0000

Data Index: 1205536 (C4 (Web Text))

Max Activating Token Index: 837

Text #5

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.2999. Min Act: -0.0000

Data Index: 186842 (C4 (Web Text))

Max Activating Token Index: 897

Text #6

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.3714. Min Act: -0.0000

Data Index: 206418 (C4 (Web Text))

Max Activating Token Index: 889

Text #7

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.3941. Min Act: -0.0000

Data Index: 1286904 (C4 (Web Text))

Max Activating Token Index: 715

Text #8

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.3088. Min Act: -0.0000

Data Index: 1847 (C4 (Web Text))

Max Activating Token Index: 1019

Text #9

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.3756. Min Act: -0.0000

Data Index: 933409 (C4 (Web Text))

Max Activating Token Index: 293

Text #10

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.4121. Min Act: -0.0000

Data Index: 1189867 (C4 (Web Text))

Max Activating Token Index: 666

Text #11

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.1663. Min Act: -0.0000

Data Index: 1073078 (C4 (Web Text))

Max Activating Token Index: 784

Text #12

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.2671. Min Act: -0.0000

Data Index: 1248046 (C4 (Web Text))

Max Activating Token Index: 1001

Text #13

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.2053. Min Act: -0.0000

Data Index: 1274595 (C4 (Web Text))

Max Activating Token Index: 310

Text #14

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.2050. Min Act: -0.0000

Data Index: 71068 (C4 (Web Text))

Max Activating Token Index: 467

Text #15

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.1720. Min Act: -0.0000

Data Index: 1221850 (C4 (Web Text))

Max Activating Token Index: 465

Text #16

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.0726. Min Act: -0.0000

Data Index: 983868 (C4 (Web Text))

Max Activating Token Index: 25

Text #17

Max Range: 1.9414. Min Range: -1.9414

Max Act: 0.9677. Min Act: -0.0000

Data Index: 884040 (C4 (Web Text))

Max Activating Token Index: 836

Text #18

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.0600. Min Act: -0.0000

Data Index: 1319303 (C4 (Web Text))

Max Activating Token Index: 498

Text #19

Max Range: 1.9414. Min Range: -1.9414

Max Act: 1.0990. Min Act: -0.0000

Data Index: 365480 (C4 (Web Text))

Max Activating Token Index: 792