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

Dataset: The Pile

Neuron 901 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.7495. Min Act: -0.0000

Data Index: 648515 (The Pile)

Max Activating Token Index: 1003

Text #1

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6979. Min Act: -0.0000

Data Index: 1660311 (The Pile)

Max Activating Token Index: 192

Text #2

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6370. Min Act: -0.0000

Data Index: 1035324 (The Pile)

Max Activating Token Index: 1004

Text #3

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5908. Min Act: -0.0000

Data Index: 1086557 (The Pile)

Max Activating Token Index: 150

Text #4

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6460. Min Act: 0.0000

Data Index: 16699 (The Pile)

Max Activating Token Index: 596

Text #5

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6141. Min Act: -0.0000

Data Index: 663449 (The Pile)

Max Activating Token Index: 584

Text #6

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6155. Min Act: -0.0000

Data Index: 1982980 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.6016. Min Act: -0.0000

Data Index: 934094 (The Pile)

Max Activating Token Index: 931

Text #8

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5940. Min Act: -0.0000

Data Index: 544888 (The Pile)

Max Activating Token Index: 19

Text #9

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5813. Min Act: -0.0000

Data Index: 1313405 (The Pile)

Max Activating Token Index: 274

Text #10

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5250. Min Act: -0.0000

Data Index: 1186113 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5344. Min Act: -0.0000

Data Index: 1505481 (The Pile)

Max Activating Token Index: 263

Text #12

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5531. Min Act: -0.0000

Data Index: 1198918 (The Pile)

Max Activating Token Index: 664

Text #13

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5790. Min Act: -0.0000

Data Index: 617526 (The Pile)

Max Activating Token Index: 576

Text #14

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5189. Min Act: -0.0000

Data Index: 960671 (The Pile)

Max Activating Token Index: 735

Text #15

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5180. Min Act: -0.0000

Data Index: 319805 (The Pile)

Max Activating Token Index: 860

Text #16

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.4407. Min Act: -0.0000

Data Index: 924729 (The Pile)

Max Activating Token Index: 776

Text #17

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5002. Min Act: -0.0000

Data Index: 100885 (The Pile)

Max Activating Token Index: 293

Text #18

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5132. Min Act: -0.0000

Data Index: 339606 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.7495. Min Range: -0.7495

Max Act: 0.5125. Min Act: -0.0000

Data Index: 470435 (The Pile)

Max Activating Token Index: 893