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

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

Neuron 475 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: 0.8792. Min Range: -0.8792

Max Act: 0.8792. Min Act: -0.0000

Data Index: 1230553 (C4 (Web Text))

Max Activating Token Index: 952

Text #1

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8456. Min Act: -0.0000

Data Index: 11041 (C4 (Web Text))

Max Activating Token Index: 849

Text #2

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8750. Min Act: -0.0000

Data Index: 329542 (C4 (Web Text))

Max Activating Token Index: 734

Text #3

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8638. Min Act: -0.0000

Data Index: 587645 (C4 (Web Text))

Max Activating Token Index: 945

Text #4

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8531. Min Act: -0.0000

Data Index: 48322 (C4 (Web Text))

Max Activating Token Index: 255

Text #5

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7808. Min Act: -0.0000

Data Index: 416510 (C4 (Web Text))

Max Activating Token Index: 50

Text #6

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.8003. Min Act: -0.0000

Data Index: 1030953 (C4 (Web Text))

Max Activating Token Index: 38

Text #7

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7936. Min Act: -0.0000

Data Index: 661928 (C4 (Web Text))

Max Activating Token Index: 121

Text #8

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7819. Min Act: -0.0000

Data Index: 833489 (C4 (Web Text))

Max Activating Token Index: 923

Text #9

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7739. Min Act: -0.0000

Data Index: 1099909 (C4 (Web Text))

Max Activating Token Index: 310

Text #10

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7608. Min Act: -0.0000

Data Index: 793400 (C4 (Web Text))

Max Activating Token Index: 988

Text #11

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7579. Min Act: -0.0000

Data Index: 568269 (C4 (Web Text))

Max Activating Token Index: 186

Text #12

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7534. Min Act: -0.0000

Data Index: 467766 (C4 (Web Text))

Max Activating Token Index: 487

Text #13

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7478. Min Act: -0.0000

Data Index: 865762 (C4 (Web Text))

Max Activating Token Index: 444

Text #14

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7486. Min Act: -0.0000

Data Index: 219648 (C4 (Web Text))

Max Activating Token Index: 704

Text #15

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7926. Min Act: -0.0000

Data Index: 203908 (C4 (Web Text))

Max Activating Token Index: 450

Text #16

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7192. Min Act: 0.0002

Data Index: 671378 (C4 (Web Text))

Max Activating Token Index: 353

Text #17

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7378. Min Act: -0.0000

Data Index: 903606 (C4 (Web Text))

Max Activating Token Index: 424

Text #18

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1177202 (C4 (Web Text))

Max Activating Token Index: 125

Text #19

Max Range: 0.8792. Min Range: -0.8792

Max Act: 0.7420. Min Act: -0.0000

Data Index: 831727 (C4 (Web Text))

Max Activating Token Index: 563