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

Dataset: The Pile

Neuron 3837 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: 0.6067. Min Range: -0.6067

Max Act: 0.6067. Min Act: -0.0000

Data Index: 91896 (The Pile)

Max Activating Token Index: 430

Text #1

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5592. Min Act: -0.0000

Data Index: 306133 (The Pile)

Max Activating Token Index: 271

Text #2

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.5309. Min Act: -0.0000

Data Index: 275793 (The Pile)

Max Activating Token Index: 510

Text #3

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4897. Min Act: -0.0000

Data Index: 1135754 (The Pile)

Max Activating Token Index: 273

Text #4

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4834. Min Act: -0.0000

Data Index: 1317654 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4604. Min Act: -0.0000

Data Index: 1189820 (The Pile)

Max Activating Token Index: 508

Text #6

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4730. Min Act: -0.0000

Data Index: 527946 (The Pile)

Max Activating Token Index: 961

Text #7

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4496. Min Act: -0.0000

Data Index: 1153832 (The Pile)

Max Activating Token Index: 648

Text #8

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4069. Min Act: -0.0000

Data Index: 231534 (The Pile)

Max Activating Token Index: 686

Text #9

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4088. Min Act: -0.0000

Data Index: 225640 (The Pile)

Max Activating Token Index: 728

Text #10

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4080. Min Act: -0.0000

Data Index: 1090671 (The Pile)

Max Activating Token Index: 670

Text #11

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4310. Min Act: -0.0000

Data Index: 190773 (The Pile)

Max Activating Token Index: 179

Text #12

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3949. Min Act: -0.0000

Data Index: 1663304 (The Pile)

Max Activating Token Index: 575

Text #13

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3899. Min Act: -0.0000

Data Index: 1273770 (The Pile)

Max Activating Token Index: 954

Text #14

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4005. Min Act: -0.0000

Data Index: 1567313 (The Pile)

Max Activating Token Index: 957

Text #15

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3528. Min Act: -0.0000

Data Index: 1139285 (The Pile)

Max Activating Token Index: 931

Text #16

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3861. Min Act: -0.0000

Data Index: 1072394 (The Pile)

Max Activating Token Index: 865

Text #17

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3638. Min Act: -0.0000

Data Index: 101132 (The Pile)

Max Activating Token Index: 244

Text #18

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.4053. Min Act: -0.0000

Data Index: 1389313 (The Pile)

Max Activating Token Index: 821

Text #19

Max Range: 0.6067. Min Range: -0.6067

Max Act: 0.3523. Min Act: -0.0000

Data Index: 418812 (The Pile)

Max Activating Token Index: 364