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

Dataset: The Pile

Neuron 3066 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.9567. Min Act: -0.0000

Data Index: 97814 (The Pile)

Max Activating Token Index: 822

Text #1

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7727. Min Act: -0.0000

Data Index: 1243513 (The Pile)

Max Activating Token Index: 981

Text #2

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7522. Min Act: -0.0000

Data Index: 1702030 (The Pile)

Max Activating Token Index: 813

Text #3

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7515. Min Act: -0.0000

Data Index: 825742 (The Pile)

Max Activating Token Index: 914

Text #4

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7269. Min Act: -0.0000

Data Index: 1435290 (The Pile)

Max Activating Token Index: 922

Text #5

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7027. Min Act: -0.0000

Data Index: 1541593 (The Pile)

Max Activating Token Index: 848

Text #6

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7304. Min Act: -0.0000

Data Index: 1643533 (The Pile)

Max Activating Token Index: 787

Text #7

Max Range: 5.1097. Min Range: -5.1097

Max Act: 5.1097. Min Act: -0.0000

Data Index: 1036757 (The Pile)

Max Activating Token Index: 1011

Text #8

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.9697. Min Act: -0.0000

Data Index: 253770 (The Pile)

Max Activating Token Index: 981

Text #9

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.7136. Min Act: -0.0000

Data Index: 1679622 (The Pile)

Max Activating Token Index: 901

Text #10

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.6973. Min Act: -0.0000

Data Index: 1476100 (The Pile)

Max Activating Token Index: 806

Text #11

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.5416. Min Act: -0.0000

Data Index: 1487189 (The Pile)

Max Activating Token Index: 511

Text #12

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.5207. Min Act: -0.0000

Data Index: 805396 (The Pile)

Max Activating Token Index: 582

Text #13

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.4659. Min Act: -0.0000

Data Index: 1046207 (The Pile)

Max Activating Token Index: 540

Text #14

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.2414. Min Act: -0.0000

Data Index: 290072 (The Pile)

Max Activating Token Index: 677

Text #15

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.4144. Min Act: -0.0000

Data Index: 766814 (The Pile)

Max Activating Token Index: 527

Text #16

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.3853. Min Act: -0.0000

Data Index: 1225139 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.2063. Min Act: -0.0000

Data Index: 1563607 (The Pile)

Max Activating Token Index: 805

Text #18

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.1973. Min Act: -0.0000

Data Index: 1494194 (The Pile)

Max Activating Token Index: 839

Text #19

Max Range: 5.1097. Min Range: -5.1097

Max Act: 4.1919. Min Act: -0.0000

Data Index: 1142945 (The Pile)

Max Activating Token Index: 781