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

Dataset: The Pile

Neuron 1548 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: 0.8441. Min Range: -0.8441

Max Act: 0.8262. Min Act: -0.0000

Data Index: 1538401 (The Pile)

Max Activating Token Index: 56

Text #1

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7012. Min Act: -0.0000

Data Index: 1804492 (The Pile)

Max Activating Token Index: 223

Text #2

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7808. Min Act: -0.0000

Data Index: 771143 (The Pile)

Max Activating Token Index: 976

Text #3

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8394. Min Act: -0.0000

Data Index: 276657 (The Pile)

Max Activating Token Index: 682

Text #4

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7207. Min Act: -0.0000

Data Index: 210208 (The Pile)

Max Activating Token Index: 344

Text #5

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7712. Min Act: -0.0000

Data Index: 1965803 (The Pile)

Max Activating Token Index: 786

Text #6

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6777. Min Act: -0.0000

Data Index: 1466682 (The Pile)

Max Activating Token Index: 611

Text #7

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1087403 (The Pile)

Max Activating Token Index: 592

Text #8

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6963. Min Act: -0.0000

Data Index: 1738957 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6062. Min Act: -0.0000

Data Index: 921214 (The Pile)

Max Activating Token Index: 211

Text #10

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7208. Min Act: -0.0000

Data Index: 884733 (The Pile)

Max Activating Token Index: 218

Text #11

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.7063. Min Act: -0.0000

Data Index: 1383984 (The Pile)

Max Activating Token Index: 226

Text #12

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6965. Min Act: -0.0000

Data Index: 656573 (The Pile)

Max Activating Token Index: 468

Text #13

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.8441. Min Act: -0.0000

Data Index: 1026539 (The Pile)

Max Activating Token Index: 708

Text #14

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6732. Min Act: -0.0000

Data Index: 226835 (The Pile)

Max Activating Token Index: 833

Text #15

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6527. Min Act: -0.0000

Data Index: 1957470 (The Pile)

Max Activating Token Index: 653

Text #16

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6897. Min Act: -0.0000

Data Index: 961616 (The Pile)

Max Activating Token Index: 783

Text #17

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.6189. Min Act: -0.0000

Data Index: 765908 (The Pile)

Max Activating Token Index: 902

Text #18

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5861. Min Act: -0.0000

Data Index: 275334 (The Pile)

Max Activating Token Index: 731

Text #19

Max Range: 0.8441. Min Range: -0.8441

Max Act: 0.5868. Min Act: -0.0000

Data Index: 1664878 (The Pile)

Max Activating Token Index: 908