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

Dataset: The Pile

Neuron 3610 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4428. Min Act: -0.0000

Data Index: 1386219 (The Pile)

Max Activating Token Index: 524

Text #1

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4563. Min Act: -0.0000

Data Index: 119187 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2288. Min Act: -0.0000

Data Index: 1560721 (The Pile)

Max Activating Token Index: 1012

Text #3

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4181. Min Act: -0.0000

Data Index: 436258 (The Pile)

Max Activating Token Index: 146

Text #4

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4580. Min Act: -0.0000

Data Index: 1774877 (The Pile)

Max Activating Token Index: 780

Text #5

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4914. Min Act: -0.0000

Data Index: 1503491 (The Pile)

Max Activating Token Index: 496

Text #6

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2598. Min Act: -0.0000

Data Index: 455674 (The Pile)

Max Activating Token Index: 87

Text #7

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.4057. Min Act: -0.0000

Data Index: 1522447 (The Pile)

Max Activating Token Index: 656

Text #8

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2984. Min Act: -0.0000

Data Index: 1183681 (The Pile)

Max Activating Token Index: 492

Text #9

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2514. Min Act: -0.0000

Data Index: 1956668 (The Pile)

Max Activating Token Index: 50

Text #10

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2801. Min Act: -0.0000

Data Index: 642683 (The Pile)

Max Activating Token Index: 587

Text #11

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3015. Min Act: -0.0000

Data Index: 1027686 (The Pile)

Max Activating Token Index: 564

Text #12

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.1912. Min Act: -0.0000

Data Index: 549035 (The Pile)

Max Activating Token Index: 305

Text #13

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2107. Min Act: -0.0000

Data Index: 135881 (The Pile)

Max Activating Token Index: 849

Text #14

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.3072. Min Act: -0.0000

Data Index: 1621906 (The Pile)

Max Activating Token Index: 458

Text #15

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2954. Min Act: -0.0000

Data Index: 1060768 (The Pile)

Max Activating Token Index: 859

Text #16

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2268. Min Act: -0.0000

Data Index: 1245174 (The Pile)

Max Activating Token Index: 386

Text #17

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.1970. Min Act: -0.0000

Data Index: 1856426 (The Pile)

Max Activating Token Index: 333

Text #18

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.2028. Min Act: -0.0000

Data Index: 308078 (The Pile)

Max Activating Token Index: 833

Text #19

Max Range: 1.4914. Min Range: -1.4914

Max Act: 1.1466. Min Act: -0.0000

Data Index: 599736 (The Pile)

Max Activating Token Index: 852