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

Dataset: The Pile

Neuron 1526 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: 1.1841. Min Range: -1.1841

Max Act: 1.1841. Min Act: -0.0000

Data Index: 1639272 (The Pile)

Max Activating Token Index: 20

Text #1

Max Range: 1.1841. Min Range: -1.1841

Max Act: 1.0743. Min Act: -0.0000

Data Index: 818159 (The Pile)

Max Activating Token Index: 587

Text #2

Max Range: 1.1841. Min Range: -1.1841

Max Act: 1.0334. Min Act: -0.0000

Data Index: 1103103 (The Pile)

Max Activating Token Index: 355

Text #3

Max Range: 1.1841. Min Range: -1.1841

Max Act: 1.0516. Min Act: -0.0000

Data Index: 950643 (The Pile)

Max Activating Token Index: 527

Text #4

Max Range: 1.1841. Min Range: -1.1841

Max Act: 1.0200. Min Act: -0.0000

Data Index: 1278432 (The Pile)

Max Activating Token Index: 349

Text #5

Max Range: 1.1841. Min Range: -1.1841

Max Act: 1.0595. Min Act: -0.0000

Data Index: 788891 (The Pile)

Max Activating Token Index: 770

Text #6

Max Range: 1.1841. Min Range: -1.1841

Max Act: 1.0808. Min Act: -0.0000

Data Index: 49886 (The Pile)

Max Activating Token Index: 6

Text #7

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.9218. Min Act: -0.0000

Data Index: 762840 (The Pile)

Max Activating Token Index: 969

Text #8

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8328. Min Act: -0.0000

Data Index: 919470 (The Pile)

Max Activating Token Index: 823

Text #9

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.7856. Min Act: -0.0000

Data Index: 354124 (The Pile)

Max Activating Token Index: 764

Text #10

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.9276. Min Act: -0.0000

Data Index: 1442577 (The Pile)

Max Activating Token Index: 249

Text #11

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8484. Min Act: -0.0000

Data Index: 1398782 (The Pile)

Max Activating Token Index: 166

Text #12

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.9447. Min Act: -0.0000

Data Index: 1562602 (The Pile)

Max Activating Token Index: 636

Text #13

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8069. Min Act: -0.0000

Data Index: 1008049 (The Pile)

Max Activating Token Index: 846

Text #14

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.9092. Min Act: -0.0000

Data Index: 1812821 (The Pile)

Max Activating Token Index: 533

Text #15

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.9225. Min Act: -0.0000

Data Index: 837521 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8991. Min Act: -0.0000

Data Index: 1800483 (The Pile)

Max Activating Token Index: 971

Text #17

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8010. Min Act: -0.0000

Data Index: 1615838 (The Pile)

Max Activating Token Index: 888

Text #18

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8552. Min Act: -0.0000

Data Index: 986417 (The Pile)

Max Activating Token Index: 109

Text #19

Max Range: 1.1841. Min Range: -1.1841

Max Act: 0.8145. Min Act: -0.0000

Data Index: 1627085 (The Pile)

Max Activating Token Index: 342