Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 538 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.4288. Min Act: -0.0000

Data Index: 1539849 (The Pile)

Max Activating Token Index: 782

Text #1

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.2100. Min Act: -0.0000

Data Index: 1148026 (The Pile)

Max Activating Token Index: 656

Text #2

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.2901. Min Act: -0.0000

Data Index: 1145365 (The Pile)

Max Activating Token Index: 489

Text #3

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1245. Min Act: -0.0000

Data Index: 954715 (The Pile)

Max Activating Token Index: 1020

Text #4

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.2007. Min Act: -0.0000

Data Index: 1672906 (The Pile)

Max Activating Token Index: 704

Text #5

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.2143. Min Act: -0.0000

Data Index: 1587520 (The Pile)

Max Activating Token Index: 755

Text #6

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1702. Min Act: -0.0000

Data Index: 1904919 (The Pile)

Max Activating Token Index: 937

Text #7

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1512. Min Act: -0.0000

Data Index: 1872486 (The Pile)

Max Activating Token Index: 558

Text #8

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1066. Min Act: -0.0000

Data Index: 1114380 (The Pile)

Max Activating Token Index: 457

Text #9

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1886. Min Act: -0.0000

Data Index: 1474402 (The Pile)

Max Activating Token Index: 1019

Text #10

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1097. Min Act: -0.0000

Data Index: 428868 (The Pile)

Max Activating Token Index: 836

Text #11

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.0997. Min Act: -0.0000

Data Index: 1923795 (The Pile)

Max Activating Token Index: 618

Text #12

Max Range: 1.4288. Min Range: -1.4288

Max Act: 0.9711. Min Act: -0.0000

Data Index: 637018 (The Pile)

Max Activating Token Index: 413

Text #13

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.0935. Min Act: -0.0000

Data Index: 213049 (The Pile)

Max Activating Token Index: 968

Text #14

Max Range: 1.4288. Min Range: -1.4288

Max Act: 0.9828. Min Act: -0.0000

Data Index: 260583 (The Pile)

Max Activating Token Index: 912

Text #15

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.0445. Min Act: -0.0000

Data Index: 183572 (The Pile)

Max Activating Token Index: 817

Text #16

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.0146. Min Act: -0.0000

Data Index: 1258776 (The Pile)

Max Activating Token Index: 409

Text #17

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.0921. Min Act: -0.0000

Data Index: 761381 (The Pile)

Max Activating Token Index: 575

Text #18

Max Range: 1.4288. Min Range: -1.4288

Max Act: 1.1742. Min Act: -0.0000

Data Index: 513438 (The Pile)

Max Activating Token Index: 725

Text #19

Max Range: 1.4288. Min Range: -1.4288

Max Act: 0.9279. Min Act: -0.0000

Data Index: 1901606 (The Pile)

Max Activating Token Index: 950