Model: SoLU Model: 4 Layers, 2048 Neurons per Layer

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

Neuron 1525 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-4l')

Text #0

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0854. Min Act: -0.0005

Data Index: 453715 (C4 (Web Text))

Max Activating Token Index: 810

Text #1

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0854. Min Act: -0.0005

Data Index: 876871 (C4 (Web Text))

Max Activating Token Index: 251

Text #2

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0875. Min Act: -0.0005

Data Index: 472878 (C4 (Web Text))

Max Activating Token Index: 354

Text #3

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0838. Min Act: -0.0005

Data Index: 1293013 (C4 (Web Text))

Max Activating Token Index: 152

Text #4

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0870. Min Act: -0.0005

Data Index: 433096 (C4 (Web Text))

Max Activating Token Index: 280

Text #5

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0814. Min Act: -0.0005

Data Index: 945536 (C4 (Web Text))

Max Activating Token Index: 765

Text #6

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0816. Min Act: -0.0005

Data Index: 1249808 (C4 (Web Text))

Max Activating Token Index: 398

Text #7

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0812. Min Act: -0.0005

Data Index: 1260747 (C4 (Web Text))

Max Activating Token Index: 104

Text #8

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0828. Min Act: -0.0005

Data Index: 1163261 (C4 (Web Text))

Max Activating Token Index: 391

Text #9

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0813. Min Act: -0.0005

Data Index: 1352843 (C4 (Web Text))

Max Activating Token Index: 388

Text #10

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0812. Min Act: -0.0005

Data Index: 1150208 (C4 (Web Text))

Max Activating Token Index: 91

Text #11

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0807. Min Act: -0.0005

Data Index: 318831 (C4 (Web Text))

Max Activating Token Index: 935

Text #12

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0785. Min Act: -0.0005

Data Index: 114768 (C4 (Web Text))

Max Activating Token Index: 295

Text #13

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0787. Min Act: -0.0005

Data Index: 380475 (C4 (Web Text))

Max Activating Token Index: 427

Text #14

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0810. Min Act: -0.0005

Data Index: 88257 (C4 (Web Text))

Max Activating Token Index: 180

Text #15

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0779. Min Act: -0.0005

Data Index: 69605 (C4 (Web Text))

Max Activating Token Index: 158

Text #16

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0761. Min Act: -0.0005

Data Index: 1003767 (C4 (Web Text))

Max Activating Token Index: 799

Text #17

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0774. Min Act: -0.0005

Data Index: 1121999 (C4 (Web Text))

Max Activating Token Index: 71

Text #18

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0755. Min Act: -0.0005

Data Index: 33437 (C4 (Web Text))

Max Activating Token Index: 688

Text #19

Max Range: 0.0875. Min Range: -0.0875

Max Act: 0.0783. Min Act: -0.0005

Data Index: 409940 (C4 (Web Text))

Max Activating Token Index: 390