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

Dataset: The Pile

Neuron 1823 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.8819. Min Act: -0.0000

Data Index: 923183 (The Pile)

Max Activating Token Index: 145

Text #1

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.9914. Min Act: -0.0000

Data Index: 728031 (The Pile)

Max Activating Token Index: 553

Text #2

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.8742. Min Act: -0.0000

Data Index: 74141 (The Pile)

Max Activating Token Index: 897

Text #3

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7992. Min Act: -0.0000

Data Index: 727908 (The Pile)

Max Activating Token Index: 594

Text #4

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7949. Min Act: -0.0000

Data Index: 1674358 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7580. Min Act: -0.0000

Data Index: 1385135 (The Pile)

Max Activating Token Index: 687

Text #6

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7930. Min Act: -0.0000

Data Index: 782906 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.8011. Min Act: -0.0000

Data Index: 1427189 (The Pile)

Max Activating Token Index: 75

Text #8

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7579. Min Act: -0.0000

Data Index: 1221366 (The Pile)

Max Activating Token Index: 30

Text #9

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7505. Min Act: -0.0000

Data Index: 1766347 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7126. Min Act: -0.0000

Data Index: 574219 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7041. Min Act: -0.0000

Data Index: 1435355 (The Pile)

Max Activating Token Index: 90

Text #12

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7734. Min Act: -0.0000

Data Index: 439740 (The Pile)

Max Activating Token Index: 437

Text #13

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6789. Min Act: -0.0000

Data Index: 1803900 (The Pile)

Max Activating Token Index: 376

Text #14

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6919. Min Act: -0.0000

Data Index: 1242644 (The Pile)

Max Activating Token Index: 264

Text #15

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6887. Min Act: -0.0000

Data Index: 1581132 (The Pile)

Max Activating Token Index: 612

Text #16

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6581. Min Act: -0.0000

Data Index: 1961934 (The Pile)

Max Activating Token Index: 636

Text #17

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6338. Min Act: -0.0000

Data Index: 743355 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6140. Min Act: -0.0000

Data Index: 1911145 (The Pile)

Max Activating Token Index: 928

Text #19

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7488. Min Act: -0.0000

Data Index: 885653 (The Pile)

Max Activating Token Index: 794