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

Dataset: The Pile

Neuron 3992 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: 1.8839. Min Range: -1.8839

Max Act: 1.8323. Min Act: -0.0000

Data Index: 420513 (The Pile)

Max Activating Token Index: 135

Text #1

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.8164. Min Act: -0.0000

Data Index: 941422 (The Pile)

Max Activating Token Index: 1001

Text #2

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.8839. Min Act: -0.0000

Data Index: 1190051 (The Pile)

Max Activating Token Index: 885

Text #3

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.8730. Min Act: -0.0000

Data Index: 1659975 (The Pile)

Max Activating Token Index: 528

Text #4

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.8492. Min Act: -0.0000

Data Index: 935457 (The Pile)

Max Activating Token Index: 619

Text #5

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7670. Min Act: -0.0000

Data Index: 1214316 (The Pile)

Max Activating Token Index: 906

Text #6

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7663. Min Act: -0.0000

Data Index: 860088 (The Pile)

Max Activating Token Index: 700

Text #7

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5037. Min Act: -0.0000

Data Index: 712139 (The Pile)

Max Activating Token Index: 529

Text #8

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6452. Min Act: -0.0000

Data Index: 1147558 (The Pile)

Max Activating Token Index: 319

Text #9

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5502. Min Act: -0.0000

Data Index: 1783026 (The Pile)

Max Activating Token Index: 911

Text #10

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7130. Min Act: -0.0000

Data Index: 1975492 (The Pile)

Max Activating Token Index: 423

Text #11

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.7036. Min Act: -0.0000

Data Index: 209723 (The Pile)

Max Activating Token Index: 1002

Text #12

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6877. Min Act: -0.0000

Data Index: 155182 (The Pile)

Max Activating Token Index: 249

Text #13

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5924. Min Act: -0.0000

Data Index: 166723 (The Pile)

Max Activating Token Index: 771

Text #14

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5912. Min Act: -0.0000

Data Index: 754626 (The Pile)

Max Activating Token Index: 1020

Text #15

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.6763. Min Act: -0.0000

Data Index: 1657686 (The Pile)

Max Activating Token Index: 48

Text #16

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.8633. Min Act: -0.0000

Data Index: 617192 (The Pile)

Max Activating Token Index: 881

Text #17

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.4935. Min Act: -0.0000

Data Index: 1525151 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5733. Min Act: -0.0000

Data Index: 199575 (The Pile)

Max Activating Token Index: 882

Text #19

Max Range: 1.8839. Min Range: -1.8839

Max Act: 1.5813. Min Act: -0.0000

Data Index: 923427 (The Pile)

Max Activating Token Index: 710