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

Dataset: The Pile

Neuron 567 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.6024. Min Act: -0.0000

Data Index: 489835 (The Pile)

Max Activating Token Index: 408

Text #1

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5186. Min Act: -0.0000

Data Index: 1962886 (The Pile)

Max Activating Token Index: 425

Text #2

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5426. Min Act: 0.0000

Data Index: 1240822 (The Pile)

Max Activating Token Index: 420

Text #3

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.6017. Min Act: -0.0000

Data Index: 1933125 (The Pile)

Max Activating Token Index: 187

Text #4

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5479. Min Act: -0.0000

Data Index: 461777 (The Pile)

Max Activating Token Index: 842

Text #5

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5021. Min Act: -0.0000

Data Index: 617436 (The Pile)

Max Activating Token Index: 655

Text #6

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5499. Min Act: -0.0000

Data Index: 1057516 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4695. Min Act: 0.0000

Data Index: 1672780 (The Pile)

Max Activating Token Index: 550

Text #8

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4910. Min Act: -0.0000

Data Index: 822855 (The Pile)

Max Activating Token Index: 870

Text #9

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5191. Min Act: -0.0000

Data Index: 304700 (The Pile)

Max Activating Token Index: 580

Text #10

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.5093. Min Act: -0.0000

Data Index: 1798836 (The Pile)

Max Activating Token Index: 294

Text #11

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4870. Min Act: -0.0000

Data Index: 1844195 (The Pile)

Max Activating Token Index: 977

Text #12

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4853. Min Act: -0.0000

Data Index: 1221661 (The Pile)

Max Activating Token Index: 473

Text #13

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4707. Min Act: -0.0000

Data Index: 843704 (The Pile)

Max Activating Token Index: 784

Text #14

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4697. Min Act: 0.0000

Data Index: 1005122 (The Pile)

Max Activating Token Index: 708

Text #15

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4998. Min Act: -0.0000

Data Index: 1376178 (The Pile)

Max Activating Token Index: 690

Text #16

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4686. Min Act: 0.0000

Data Index: 1796022 (The Pile)

Max Activating Token Index: 610

Text #17

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4921. Min Act: -0.0000

Data Index: 221748 (The Pile)

Max Activating Token Index: 918

Text #18

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4817. Min Act: 0.0000

Data Index: 378697 (The Pile)

Max Activating Token Index: 428

Text #19

Max Range: 0.6024. Min Range: -0.6024

Max Act: 0.4747. Min Act: -0.0000

Data Index: 387071 (The Pile)

Max Activating Token Index: 565