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

Dataset: The Pile

Neuron 23 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: 1.9974. Min Range: -1.9974

Max Act: 1.9974. Min Act: -0.0000

Data Index: 1803731 (The Pile)

Max Activating Token Index: 166

Text #1

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.6562. Min Act: -0.0000

Data Index: 1313401 (The Pile)

Max Activating Token Index: 6

Text #2

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.4849. Min Act: -0.0000

Data Index: 470163 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.4542. Min Act: -0.0000

Data Index: 1784840 (The Pile)

Max Activating Token Index: 58

Text #4

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.5103. Min Act: -0.0000

Data Index: 1215819 (The Pile)

Max Activating Token Index: 181

Text #5

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.3366. Min Act: -0.0000

Data Index: 899034 (The Pile)

Max Activating Token Index: 1000

Text #6

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.3638. Min Act: -0.0000

Data Index: 622476 (The Pile)

Max Activating Token Index: 20

Text #7

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.2471. Min Act: -0.0000

Data Index: 14250 (The Pile)

Max Activating Token Index: 708

Text #8

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.4105. Min Act: -0.0000

Data Index: 456101 (The Pile)

Max Activating Token Index: 965

Text #9

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.5790. Min Act: -0.0000

Data Index: 79696 (The Pile)

Max Activating Token Index: 180

Text #10

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.3673. Min Act: -0.0000

Data Index: 1726763 (The Pile)

Max Activating Token Index: 1010

Text #11

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.3179. Min Act: -0.0000

Data Index: 883627 (The Pile)

Max Activating Token Index: 520

Text #12

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.3865. Min Act: -0.0000

Data Index: 599499 (The Pile)

Max Activating Token Index: 829

Text #13

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.1909. Min Act: -0.0000

Data Index: 509046 (The Pile)

Max Activating Token Index: 1013

Text #14

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.3951. Min Act: -0.0000

Data Index: 709107 (The Pile)

Max Activating Token Index: 695

Text #15

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.2898. Min Act: -0.0000

Data Index: 536157 (The Pile)

Max Activating Token Index: 676

Text #16

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.2884. Min Act: -0.0000

Data Index: 523483 (The Pile)

Max Activating Token Index: 334

Text #17

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.1948. Min Act: -0.0000

Data Index: 503226 (The Pile)

Max Activating Token Index: 36

Text #18

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.1456. Min Act: -0.0000

Data Index: 1112926 (The Pile)

Max Activating Token Index: 285

Text #19

Max Range: 1.9974. Min Range: -1.9974

Max Act: 1.2501. Min Act: -0.0000

Data Index: 1475325 (The Pile)

Max Activating Token Index: 383