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

Dataset: The Pile

Neuron 294 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: 0.8754. Min Range: -0.8754

Max Act: 0.8130. Min Act: -0.0000

Data Index: 1854565 (The Pile)

Max Activating Token Index: 517

Text #1

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7990. Min Act: -0.0000

Data Index: 893464 (The Pile)

Max Activating Token Index: 191

Text #2

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8099. Min Act: -0.0000

Data Index: 1032699 (The Pile)

Max Activating Token Index: 473

Text #3

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8754. Min Act: -0.0000

Data Index: 1938251 (The Pile)

Max Activating Token Index: 771

Text #4

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7673. Min Act: -0.0000

Data Index: 270688 (The Pile)

Max Activating Token Index: 763

Text #5

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.8382. Min Act: -0.0000

Data Index: 614961 (The Pile)

Max Activating Token Index: 959

Text #6

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7326. Min Act: -0.0000

Data Index: 566540 (The Pile)

Max Activating Token Index: 745

Text #7

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7562. Min Act: -0.0000

Data Index: 1906208 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7357. Min Act: -0.0000

Data Index: 932362 (The Pile)

Max Activating Token Index: 921

Text #9

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7245. Min Act: -0.0000

Data Index: 365143 (The Pile)

Max Activating Token Index: 1021

Text #10

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6453. Min Act: -0.0000

Data Index: 1915119 (The Pile)

Max Activating Token Index: 869

Text #11

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7118. Min Act: -0.0000

Data Index: 697823 (The Pile)

Max Activating Token Index: 800

Text #12

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7050. Min Act: -0.0000

Data Index: 627448 (The Pile)

Max Activating Token Index: 888

Text #13

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6689. Min Act: -0.0000

Data Index: 1038708 (The Pile)

Max Activating Token Index: 653

Text #14

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7121. Min Act: -0.0000

Data Index: 1572844 (The Pile)

Max Activating Token Index: 995

Text #15

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6664. Min Act: -0.0000

Data Index: 431725 (The Pile)

Max Activating Token Index: 419

Text #16

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7230. Min Act: -0.0000

Data Index: 1631118 (The Pile)

Max Activating Token Index: 901

Text #17

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6645. Min Act: -0.0000

Data Index: 1035772 (The Pile)

Max Activating Token Index: 477

Text #18

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.7701. Min Act: -0.0000

Data Index: 1716469 (The Pile)

Max Activating Token Index: 579

Text #19

Max Range: 0.8754. Min Range: -0.8754

Max Act: 0.6754. Min Act: -0.0000

Data Index: 1257117 (The Pile)

Max Activating Token Index: 560