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

Dataset: The Pile

Neuron 4279 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: 1.9908. Min Range: -1.9908

Max Act: 1.9908. Min Act: -0.0000

Data Index: 956725 (The Pile)

Max Activating Token Index: 46

Text #1

Max Range: 1.9908. Min Range: -1.9908

Max Act: 1.5745. Min Act: -0.0000

Data Index: 106178 (The Pile)

Max Activating Token Index: 680

Text #2

Max Range: 1.9908. Min Range: -1.9908

Max Act: 1.5065. Min Act: -0.0000

Data Index: 624241 (The Pile)

Max Activating Token Index: 347

Text #3

Max Range: 1.9908. Min Range: -1.9908

Max Act: 1.4801. Min Act: -0.0000

Data Index: 1926524 (The Pile)

Max Activating Token Index: 1014

Text #4

Max Range: 1.9908. Min Range: -1.9908

Max Act: 1.3525. Min Act: -0.0000

Data Index: 1872683 (The Pile)

Max Activating Token Index: 317

Text #5

Max Range: 1.9908. Min Range: -1.9908

Max Act: 1.1641. Min Act: -0.0000

Data Index: 1900484 (The Pile)

Max Activating Token Index: 59

Text #6

Max Range: 1.9908. Min Range: -1.9908

Max Act: 1.1005. Min Act: -0.0000

Data Index: 630440 (The Pile)

Max Activating Token Index: 157

Text #7

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.9716. Min Act: -0.0000

Data Index: 1202971 (The Pile)

Max Activating Token Index: 935

Text #8

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.9510. Min Act: -0.0000

Data Index: 218873 (The Pile)

Max Activating Token Index: 982

Text #9

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.9096. Min Act: -0.0000

Data Index: 775583 (The Pile)

Max Activating Token Index: 913

Text #10

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7590. Min Act: -0.0000

Data Index: 1668203 (The Pile)

Max Activating Token Index: 831

Text #11

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.8052. Min Act: -0.0000

Data Index: 177264 (The Pile)

Max Activating Token Index: 802

Text #12

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.6587. Min Act: -0.0000

Data Index: 1090468 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7865. Min Act: -0.0000

Data Index: 286416 (The Pile)

Max Activating Token Index: 1000

Text #14

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7475. Min Act: -0.0000

Data Index: 1612634 (The Pile)

Max Activating Token Index: 927

Text #15

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7133. Min Act: -0.0000

Data Index: 1877688 (The Pile)

Max Activating Token Index: 41

Text #16

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7075. Min Act: -0.0000

Data Index: 1020961 (The Pile)

Max Activating Token Index: 50

Text #17

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7307. Min Act: -0.0000

Data Index: 1384923 (The Pile)

Max Activating Token Index: 982

Text #18

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7086. Min Act: -0.0000

Data Index: 871977 (The Pile)

Max Activating Token Index: 889

Text #19

Max Range: 1.9908. Min Range: -1.9908

Max Act: 0.7825. Min Act: -0.0000

Data Index: 543874 (The Pile)

Max Activating Token Index: 218