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

Dataset: The Pile

Neuron 744 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: 0.8011. Min Range: -0.8011

Max Act: 0.7888. Min Act: -0.0000

Data Index: 219813 (The Pile)

Max Activating Token Index: 124

Text #1

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.8011. Min Act: -0.0000

Data Index: 209477 (The Pile)

Max Activating Token Index: 268

Text #2

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.7189. Min Act: -0.0000

Data Index: 1762248 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.7229. Min Act: -0.0000

Data Index: 571849 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1933889 (The Pile)

Max Activating Token Index: 1012

Text #5

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6001. Min Act: -0.0000

Data Index: 339473 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6334. Min Act: -0.0000

Data Index: 1562864 (The Pile)

Max Activating Token Index: 46

Text #7

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6354. Min Act: -0.0000

Data Index: 1375218 (The Pile)

Max Activating Token Index: 347

Text #8

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6059. Min Act: -0.0000

Data Index: 603964 (The Pile)

Max Activating Token Index: 843

Text #9

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5938. Min Act: 0.0000

Data Index: 972716 (The Pile)

Max Activating Token Index: 519

Text #10

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5907. Min Act: 0.0000

Data Index: 1677454 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.6007. Min Act: -0.0000

Data Index: 1357999 (The Pile)

Max Activating Token Index: 237

Text #12

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5773. Min Act: -0.0000

Data Index: 434637 (The Pile)

Max Activating Token Index: 268

Text #13

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5806. Min Act: 0.0000

Data Index: 34664 (The Pile)

Max Activating Token Index: 233

Text #14

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5740. Min Act: -0.0000

Data Index: 923982 (The Pile)

Max Activating Token Index: 426

Text #15

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5713. Min Act: -0.0000

Data Index: 113739 (The Pile)

Max Activating Token Index: 597

Text #16

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5765. Min Act: -0.0000

Data Index: 1780554 (The Pile)

Max Activating Token Index: 492

Text #17

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5685. Min Act: -0.0000

Data Index: 700690 (The Pile)

Max Activating Token Index: 78

Text #18

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5649. Min Act: -0.0000

Data Index: 1808043 (The Pile)

Max Activating Token Index: 702

Text #19

Max Range: 0.8011. Min Range: -0.8011

Max Act: 0.5645. Min Act: 0.0000

Data Index: 691839 (The Pile)

Max Activating Token Index: 1017