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

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

Neuron 3504 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: 2.7873. Min Range: -2.7873

Max Act: 2.7873. Min Act: -0.0000

Data Index: 653668 (C4 (Web Text))

Max Activating Token Index: 795

Text #1

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.5615. Min Act: -0.0000

Data Index: 288347 (C4 (Web Text))

Max Activating Token Index: 748

Text #2

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.6853. Min Act: -0.0000

Data Index: 65643 (C4 (Web Text))

Max Activating Token Index: 623

Text #3

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.3722. Min Act: -0.0000

Data Index: 606392 (C4 (Web Text))

Max Activating Token Index: 817

Text #4

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.3333. Min Act: -0.0000

Data Index: 258023 (C4 (Web Text))

Max Activating Token Index: 1013

Text #5

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.4240. Min Act: -0.0000

Data Index: 971694 (C4 (Web Text))

Max Activating Token Index: 254

Text #6

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.3013. Min Act: -0.0000

Data Index: 857884 (C4 (Web Text))

Max Activating Token Index: 509

Text #7

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.2888. Min Act: -0.0000

Data Index: 1234444 (C4 (Web Text))

Max Activating Token Index: 155

Text #8

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.2368. Min Act: -0.0000

Data Index: 1316266 (C4 (Web Text))

Max Activating Token Index: 220

Text #9

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.2050. Min Act: -0.0000

Data Index: 852742 (C4 (Web Text))

Max Activating Token Index: 353

Text #10

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.2010. Min Act: -0.0000

Data Index: 472307 (C4 (Web Text))

Max Activating Token Index: 861

Text #11

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.0419. Min Act: -0.0000

Data Index: 1279727 (C4 (Web Text))

Max Activating Token Index: 144

Text #12

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.1471. Min Act: -0.0000

Data Index: 667570 (C4 (Web Text))

Max Activating Token Index: 623

Text #13

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.1197. Min Act: -0.0000

Data Index: 682165 (C4 (Web Text))

Max Activating Token Index: 76

Text #14

Max Range: 2.7873. Min Range: -2.7873

Max Act: 2.0941. Min Act: -0.0000

Data Index: 543387 (C4 (Web Text))

Max Activating Token Index: 223

Text #15

Max Range: 2.7873. Min Range: -2.7873

Max Act: 1.9894. Min Act: -0.0000

Data Index: 711883 (C4 (Web Text))

Max Activating Token Index: 164

Text #16

Max Range: 2.7873. Min Range: -2.7873

Max Act: 1.9183. Min Act: -0.0000

Data Index: 752480 (C4 (Web Text))

Max Activating Token Index: 902

Text #17

Max Range: 2.7873. Min Range: -2.7873

Max Act: 1.9909. Min Act: -0.0000

Data Index: 491247 (C4 (Web Text))

Max Activating Token Index: 528

Text #18

Max Range: 2.7873. Min Range: -2.7873

Max Act: 1.9867. Min Act: -0.0000

Data Index: 467039 (C4 (Web Text))

Max Activating Token Index: 795

Text #19

Max Range: 2.7873. Min Range: -2.7873

Max Act: 1.8163. Min Act: -0.0000

Data Index: 702266 (C4 (Web Text))

Max Activating Token Index: 115