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

Dataset: The Pile

Neuron 1285 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7770. Min Act: -0.0000

Data Index: 828818 (The Pile)

Max Activating Token Index: 890

Text #1

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7722. Min Act: -0.0000

Data Index: 1908237 (The Pile)

Max Activating Token Index: 905

Text #2

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.7581. Min Act: -0.0000

Data Index: 1306263 (The Pile)

Max Activating Token Index: 884

Text #3

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6765. Min Act: -0.0000

Data Index: 1066174 (The Pile)

Max Activating Token Index: 166

Text #4

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1574981 (The Pile)

Max Activating Token Index: 258

Text #5

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6682. Min Act: -0.0000

Data Index: 518567 (The Pile)

Max Activating Token Index: 634

Text #6

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5936. Min Act: -0.0000

Data Index: 1687391 (The Pile)

Max Activating Token Index: 411

Text #7

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6506. Min Act: -0.0000

Data Index: 1111916 (The Pile)

Max Activating Token Index: 628

Text #8

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5857. Min Act: -0.0000

Data Index: 74779 (The Pile)

Max Activating Token Index: 425

Text #9

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5768. Min Act: -0.0000

Data Index: 96720 (The Pile)

Max Activating Token Index: 563

Text #10

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.6072. Min Act: -0.0000

Data Index: 1601116 (The Pile)

Max Activating Token Index: 764

Text #11

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5841. Min Act: -0.0000

Data Index: 1918495 (The Pile)

Max Activating Token Index: 731

Text #12

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5184. Min Act: -0.0000

Data Index: 972744 (The Pile)

Max Activating Token Index: 238

Text #13

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5234. Min Act: -0.0000

Data Index: 142876 (The Pile)

Max Activating Token Index: 597

Text #14

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.4670. Min Act: -0.0000

Data Index: 1667247 (The Pile)

Max Activating Token Index: 515

Text #15

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.4789. Min Act: -0.0000

Data Index: 11450 (The Pile)

Max Activating Token Index: 553

Text #16

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.4939. Min Act: -0.0000

Data Index: 1823388 (The Pile)

Max Activating Token Index: 769

Text #17

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.4887. Min Act: -0.0000

Data Index: 1835661 (The Pile)

Max Activating Token Index: 886

Text #18

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.4838. Min Act: -0.0000

Data Index: 1849980 (The Pile)

Max Activating Token Index: 909

Text #19

Max Range: 0.7770. Min Range: -0.7770

Max Act: 0.5555. Min Act: -0.0000

Data Index: 1995794 (The Pile)

Max Activating Token Index: 866