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

Dataset: The Pile

Neuron 90 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: 0.9918. Min Range: -0.9918

Max Act: 0.9918. Min Act: -0.0000

Data Index: 1906585 (The Pile)

Max Activating Token Index: 454

Text #1

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.8919. Min Act: -0.0000

Data Index: 1705240 (The Pile)

Max Activating Token Index: 509

Text #2

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.8138. Min Act: -0.0000

Data Index: 1881055 (The Pile)

Max Activating Token Index: 977

Text #3

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7846. Min Act: -0.0000

Data Index: 64442 (The Pile)

Max Activating Token Index: 53

Text #4

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.8131. Min Act: -0.0000

Data Index: 512027 (The Pile)

Max Activating Token Index: 518

Text #5

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6871. Min Act: -0.0000

Data Index: 1905922 (The Pile)

Max Activating Token Index: 412

Text #6

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7583. Min Act: -0.0000

Data Index: 1511239 (The Pile)

Max Activating Token Index: 790

Text #7

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6606. Min Act: -0.0000

Data Index: 1856150 (The Pile)

Max Activating Token Index: 537

Text #8

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7121. Min Act: -0.0000

Data Index: 82468 (The Pile)

Max Activating Token Index: 83

Text #9

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.7465. Min Act: -0.0000

Data Index: 1411314 (The Pile)

Max Activating Token Index: 609

Text #10

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6531. Min Act: -0.0000

Data Index: 1813892 (The Pile)

Max Activating Token Index: 293

Text #11

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6417. Min Act: -0.0000

Data Index: 530643 (The Pile)

Max Activating Token Index: 836

Text #12

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6742. Min Act: -0.0000

Data Index: 1630713 (The Pile)

Max Activating Token Index: 639

Text #13

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6375. Min Act: -0.0000

Data Index: 227312 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6033. Min Act: -0.0000

Data Index: 449805 (The Pile)

Max Activating Token Index: 152

Text #15

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6569. Min Act: -0.0000

Data Index: 1584072 (The Pile)

Max Activating Token Index: 400

Text #16

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.5873. Min Act: -0.0000

Data Index: 889605 (The Pile)

Max Activating Token Index: 764

Text #17

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6464. Min Act: -0.0000

Data Index: 512636 (The Pile)

Max Activating Token Index: 194

Text #18

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6667. Min Act: -0.0000

Data Index: 172787 (The Pile)

Max Activating Token Index: 104

Text #19

Max Range: 0.9918. Min Range: -0.9918

Max Act: 0.6488. Min Act: -0.0000

Data Index: 762413 (The Pile)

Max Activating Token Index: 564