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

Dataset: The Pile

Neuron 3009 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.1914. Min Act: -0.0000

Data Index: 1986746 (The Pile)

Max Activating Token Index: 975

Text #1

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9724. Min Act: -0.0000

Data Index: 702765 (The Pile)

Max Activating Token Index: 995

Text #2

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9725. Min Act: -0.0000

Data Index: 1865910 (The Pile)

Max Activating Token Index: 686

Text #3

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0481. Min Act: -0.0000

Data Index: 739876 (The Pile)

Max Activating Token Index: 967

Text #4

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0766. Min Act: -0.0000

Data Index: 703392 (The Pile)

Max Activating Token Index: 331

Text #5

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0963. Min Act: -0.0000

Data Index: 1160449 (The Pile)

Max Activating Token Index: 894

Text #6

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9340. Min Act: -0.0000

Data Index: 1447715 (The Pile)

Max Activating Token Index: 657

Text #7

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9605. Min Act: -0.0000

Data Index: 1860925 (The Pile)

Max Activating Token Index: 371

Text #8

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0131. Min Act: -0.0000

Data Index: 1092890 (The Pile)

Max Activating Token Index: 445

Text #9

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9267. Min Act: -0.0000

Data Index: 1321187 (The Pile)

Max Activating Token Index: 640

Text #10

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0132. Min Act: -0.0000

Data Index: 1939694 (The Pile)

Max Activating Token Index: 504

Text #11

Max Range: 1.1914. Min Range: -1.1914

Max Act: 1.0197. Min Act: -0.0000

Data Index: 741336 (The Pile)

Max Activating Token Index: 73

Text #12

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9527. Min Act: -0.0000

Data Index: 374379 (The Pile)

Max Activating Token Index: 415

Text #13

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9353. Min Act: -0.0000

Data Index: 316316 (The Pile)

Max Activating Token Index: 567

Text #14

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9350. Min Act: -0.0000

Data Index: 602522 (The Pile)

Max Activating Token Index: 48

Text #15

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9285. Min Act: -0.0000

Data Index: 1264939 (The Pile)

Max Activating Token Index: 828

Text #16

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.9334. Min Act: -0.0000

Data Index: 1883656 (The Pile)

Max Activating Token Index: 196

Text #17

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8707. Min Act: -0.0000

Data Index: 132377 (The Pile)

Max Activating Token Index: 45

Text #18

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8959. Min Act: -0.0000

Data Index: 4515 (The Pile)

Max Activating Token Index: 1019

Text #19

Max Range: 1.1914. Min Range: -1.1914

Max Act: 0.8575. Min Act: -0.0000

Data Index: 1205697 (The Pile)

Max Activating Token Index: 70