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

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

Neuron 3348 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: 2.1909. Min Range: -2.1909

Max Act: 2.1909. Min Act: -0.0000

Data Index: 459226 (C4 (Web Text))

Max Activating Token Index: 12

Text #1

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.8632. Min Act: -0.0000

Data Index: 168695 (C4 (Web Text))

Max Activating Token Index: 837

Text #2

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.9454. Min Act: -0.0000

Data Index: 370345 (C4 (Web Text))

Max Activating Token Index: 912

Text #3

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.8120. Min Act: 0.0000

Data Index: 432012 (C4 (Web Text))

Max Activating Token Index: 144

Text #4

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.8065. Min Act: -0.0000

Data Index: 730270 (C4 (Web Text))

Max Activating Token Index: 120

Text #5

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6854. Min Act: -0.0000

Data Index: 843813 (C4 (Web Text))

Max Activating Token Index: 428

Text #6

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.7801. Min Act: 0.0000

Data Index: 133871 (C4 (Web Text))

Max Activating Token Index: 184

Text #7

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.7021. Min Act: -0.0000

Data Index: 955664 (C4 (Web Text))

Max Activating Token Index: 594

Text #8

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6786. Min Act: -0.0000

Data Index: 498627 (C4 (Web Text))

Max Activating Token Index: 907

Text #9

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6937. Min Act: -0.0000

Data Index: 780997 (C4 (Web Text))

Max Activating Token Index: 957

Text #10

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6799. Min Act: -0.0000

Data Index: 1225394 (C4 (Web Text))

Max Activating Token Index: 869

Text #11

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6469. Min Act: -0.0000

Data Index: 1122631 (C4 (Web Text))

Max Activating Token Index: 322

Text #12

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6336. Min Act: -0.0000

Data Index: 255655 (C4 (Web Text))

Max Activating Token Index: 540

Text #13

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.6208. Min Act: -0.0000

Data Index: 467031 (C4 (Web Text))

Max Activating Token Index: 567

Text #14

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.5399. Min Act: -0.0000

Data Index: 952832 (C4 (Web Text))

Max Activating Token Index: 249

Text #15

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.5344. Min Act: -0.0000

Data Index: 630019 (C4 (Web Text))

Max Activating Token Index: 527

Text #16

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.5376. Min Act: -0.0000

Data Index: 455619 (C4 (Web Text))

Max Activating Token Index: 426

Text #17

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.5361. Min Act: -0.0000

Data Index: 1155029 (C4 (Web Text))

Max Activating Token Index: 110

Text #18

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.4276. Min Act: -0.0000

Data Index: 560674 (C4 (Web Text))

Max Activating Token Index: 219

Text #19

Max Range: 2.1909. Min Range: -2.1909

Max Act: 1.5023. Min Act: -0.0000

Data Index: 796922 (C4 (Web Text))

Max Activating Token Index: 541