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

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

Neuron 369 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2757. Min Act: -0.0000

Data Index: 451335 (C4 (Web Text))

Max Activating Token Index: 677

Text #1

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2383. Min Act: -0.0000

Data Index: 990365 (C4 (Web Text))

Max Activating Token Index: 991

Text #2

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2315. Min Act: -0.0000

Data Index: 376310 (C4 (Web Text))

Max Activating Token Index: 651

Text #3

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2178. Min Act: -0.0000

Data Index: 902720 (C4 (Web Text))

Max Activating Token Index: 519

Text #4

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2158. Min Act: -0.0000

Data Index: 109508 (C4 (Web Text))

Max Activating Token Index: 106

Text #5

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2162. Min Act: -0.0000

Data Index: 935270 (C4 (Web Text))

Max Activating Token Index: 635

Text #6

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2006. Min Act: -0.0000

Data Index: 752756 (C4 (Web Text))

Max Activating Token Index: 462

Text #7

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1897. Min Act: -0.0000

Data Index: 420991 (C4 (Web Text))

Max Activating Token Index: 719

Text #8

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2006. Min Act: -0.0000

Data Index: 261088 (C4 (Web Text))

Max Activating Token Index: 908

Text #9

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1934. Min Act: -0.0000

Data Index: 532480 (C4 (Web Text))

Max Activating Token Index: 928

Text #10

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1819. Min Act: -0.0000

Data Index: 1630728 (Python Code)

Max Activating Token Index: 145

Text #11

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.2108. Min Act: -0.0000

Data Index: 945735 (C4 (Web Text))

Max Activating Token Index: 551

Text #12

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1697. Min Act: -0.0000

Data Index: 715675 (C4 (Web Text))

Max Activating Token Index: 877

Text #13

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1798. Min Act: -0.0000

Data Index: 929239 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1924. Min Act: -0.0000

Data Index: 39083 (C4 (Web Text))

Max Activating Token Index: 816

Text #15

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1756. Min Act: -0.0000

Data Index: 425163 (C4 (Web Text))

Max Activating Token Index: 750

Text #16

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1345690 (C4 (Web Text))

Max Activating Token Index: 283

Text #17

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1813. Min Act: -0.0000

Data Index: 596797 (C4 (Web Text))

Max Activating Token Index: 1012

Text #18

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1705. Min Act: -0.0000

Data Index: 697895 (C4 (Web Text))

Max Activating Token Index: 1013

Text #19

Max Range: 0.2757. Min Range: -0.2757

Max Act: 0.1650. Min Act: -0.0000

Data Index: 763563 (C4 (Web Text))

Max Activating Token Index: 309