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

Dataset: The Pile

Neuron 1034 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.8011. Min Act: -0.0000

Data Index: 592651 (The Pile)

Max Activating Token Index: 798

Text #1

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.7012. Min Act: -0.0000

Data Index: 1571415 (The Pile)

Max Activating Token Index: 394

Text #2

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5326. Min Act: -0.0000

Data Index: 116014 (The Pile)

Max Activating Token Index: 887

Text #3

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5841. Min Act: -0.0000

Data Index: 1063066 (The Pile)

Max Activating Token Index: 1007

Text #4

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5363. Min Act: -0.0000

Data Index: 1433534 (The Pile)

Max Activating Token Index: 159

Text #5

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.6196. Min Act: -0.0000

Data Index: 1710901 (The Pile)

Max Activating Token Index: 978

Text #6

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4640. Min Act: -0.0000

Data Index: 380860 (The Pile)

Max Activating Token Index: 648

Text #7

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.6519. Min Act: -0.0000

Data Index: 1919381 (The Pile)

Max Activating Token Index: 842

Text #8

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5526. Min Act: -0.0000

Data Index: 363018 (The Pile)

Max Activating Token Index: 844

Text #9

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5500. Min Act: -0.0000

Data Index: 1768777 (The Pile)

Max Activating Token Index: 144

Text #10

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.5577. Min Act: -0.0000

Data Index: 552345 (The Pile)

Max Activating Token Index: 791

Text #11

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.6231. Min Act: -0.0000

Data Index: 1153685 (The Pile)

Max Activating Token Index: 889

Text #12

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4565. Min Act: -0.0000

Data Index: 1716580 (The Pile)

Max Activating Token Index: 702

Text #13

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4517. Min Act: -0.0000

Data Index: 1600764 (The Pile)

Max Activating Token Index: 196

Text #14

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3643. Min Act: -0.0000

Data Index: 1442126 (The Pile)

Max Activating Token Index: 435

Text #15

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.3115. Min Act: -0.0000

Data Index: 1550827 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4574. Min Act: -0.0000

Data Index: 133395 (The Pile)

Max Activating Token Index: 314

Text #17

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4407. Min Act: -0.0000

Data Index: 1844353 (The Pile)

Max Activating Token Index: 879

Text #18

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4345. Min Act: -0.0000

Data Index: 1351959 (The Pile)

Max Activating Token Index: 397

Text #19

Max Range: 1.8011. Min Range: -1.8011

Max Act: 1.4263. Min Act: -0.0000

Data Index: 1499147 (The Pile)

Max Activating Token Index: 898