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

Dataset: The Pile

Neuron 4678 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.9969. Min Act: -0.0000

Data Index: 1044261 (The Pile)

Max Activating Token Index: 246

Text #1

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7969. Min Act: -0.0000

Data Index: 1615634 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.7417. Min Act: -0.0000

Data Index: 628495 (The Pile)

Max Activating Token Index: 872

Text #3

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.6479. Min Act: -0.0000

Data Index: 1929431 (The Pile)

Max Activating Token Index: 562

Text #4

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.5853. Min Act: -0.0000

Data Index: 624346 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.5975. Min Act: -0.0000

Data Index: 370390 (The Pile)

Max Activating Token Index: 58

Text #6

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.5076. Min Act: -0.0000

Data Index: 1761793 (The Pile)

Max Activating Token Index: 718

Text #7

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.5006. Min Act: -0.0000

Data Index: 1791629 (The Pile)

Max Activating Token Index: 360

Text #8

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4977. Min Act: -0.0000

Data Index: 656911 (The Pile)

Max Activating Token Index: 316

Text #9

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4581. Min Act: 0.0000

Data Index: 1244884 (The Pile)

Max Activating Token Index: 972

Text #10

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4546. Min Act: -0.0000

Data Index: 1278884 (The Pile)

Max Activating Token Index: 397

Text #11

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.5137. Min Act: -0.0000

Data Index: 1678255 (The Pile)

Max Activating Token Index: 403

Text #12

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4838. Min Act: -0.0000

Data Index: 720948 (The Pile)

Max Activating Token Index: 736

Text #13

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4116. Min Act: -0.0000

Data Index: 1509835 (The Pile)

Max Activating Token Index: 972

Text #14

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4782. Min Act: -0.0000

Data Index: 1087658 (The Pile)

Max Activating Token Index: 291

Text #15

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4498. Min Act: -0.0000

Data Index: 898720 (The Pile)

Max Activating Token Index: 779

Text #16

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.3958. Min Act: -0.0000

Data Index: 768102 (The Pile)

Max Activating Token Index: 280

Text #17

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.3828. Min Act: -0.0000

Data Index: 523323 (The Pile)

Max Activating Token Index: 730

Text #18

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4708. Min Act: -0.0000

Data Index: 1788179 (The Pile)

Max Activating Token Index: 1000

Text #19

Max Range: 0.9969. Min Range: -0.9969

Max Act: 0.4602. Min Act: -0.0000

Data Index: 670467 (The Pile)

Max Activating Token Index: 473