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

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

Neuron 3819 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.9281. Min Act: -0.0000

Data Index: 355211 (C4 (Web Text))

Max Activating Token Index: 703

Text #1

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8978. Min Act: -0.0000

Data Index: 914048 (C4 (Web Text))

Max Activating Token Index: 811

Text #2

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8489. Min Act: -0.0001

Data Index: 956333 (C4 (Web Text))

Max Activating Token Index: 975

Text #3

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8897. Min Act: -0.0000

Data Index: 482379 (C4 (Web Text))

Max Activating Token Index: 477

Text #4

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8562. Min Act: -0.0000

Data Index: 615618 (C4 (Web Text))

Max Activating Token Index: 487

Text #5

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8506. Min Act: -0.0000

Data Index: 1324139 (C4 (Web Text))

Max Activating Token Index: 463

Text #6

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8223. Min Act: -0.0000

Data Index: 600915 (C4 (Web Text))

Max Activating Token Index: 114

Text #7

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7821. Min Act: -0.0001

Data Index: 17376 (C4 (Web Text))

Max Activating Token Index: 80

Text #8

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7178. Min Act: -0.0000

Data Index: 1019891 (C4 (Web Text))

Max Activating Token Index: 164

Text #9

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8075. Min Act: -0.0000

Data Index: 18297 (C4 (Web Text))

Max Activating Token Index: 261

Text #10

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7695. Min Act: -0.0000

Data Index: 1040303 (C4 (Web Text))

Max Activating Token Index: 555

Text #11

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7804. Min Act: -0.0000

Data Index: 1024717 (C4 (Web Text))

Max Activating Token Index: 875

Text #12

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.8240. Min Act: -0.0000

Data Index: 974582 (C4 (Web Text))

Max Activating Token Index: 571

Text #13

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7972. Min Act: -0.0000

Data Index: 1031396 (C4 (Web Text))

Max Activating Token Index: 406

Text #14

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7712. Min Act: -0.0000

Data Index: 592843 (C4 (Web Text))

Max Activating Token Index: 859

Text #15

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7718. Min Act: -0.0000

Data Index: 455900 (C4 (Web Text))

Max Activating Token Index: 1009

Text #16

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7496. Min Act: -0.0000

Data Index: 478726 (C4 (Web Text))

Max Activating Token Index: 460

Text #17

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7703. Min Act: -0.0000

Data Index: 1014927 (C4 (Web Text))

Max Activating Token Index: 546

Text #18

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7692. Min Act: -0.0000

Data Index: 317635 (C4 (Web Text))

Max Activating Token Index: 745

Text #19

Max Range: 0.9281. Min Range: -0.9281

Max Act: 0.7666. Min Act: -0.0000

Data Index: 1144215 (C4 (Web Text))

Max Activating Token Index: 69