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

Dataset: The Pile

Neuron 568 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: 1.0285. Min Range: -1.0285

Max Act: 1.0285. Min Act: -0.0000

Data Index: 1222524 (The Pile)

Max Activating Token Index: 495

Text #1

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.7348. Min Act: -0.0000

Data Index: 302479 (The Pile)

Max Activating Token Index: 133

Text #2

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6901. Min Act: -0.0000

Data Index: 916052 (The Pile)

Max Activating Token Index: 387

Text #3

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6978. Min Act: -0.0000

Data Index: 1635444 (The Pile)

Max Activating Token Index: 725

Text #4

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6695. Min Act: -0.0000

Data Index: 626022 (The Pile)

Max Activating Token Index: 670

Text #5

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6747. Min Act: -0.0000

Data Index: 137986 (The Pile)

Max Activating Token Index: 14

Text #6

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6810. Min Act: -0.0000

Data Index: 498944 (The Pile)

Max Activating Token Index: 100

Text #7

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6044. Min Act: -0.0000

Data Index: 414646 (The Pile)

Max Activating Token Index: 111

Text #8

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6417. Min Act: -0.0000

Data Index: 121329 (The Pile)

Max Activating Token Index: 52

Text #9

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6123. Min Act: -0.0000

Data Index: 82957 (The Pile)

Max Activating Token Index: 904

Text #10

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6634. Min Act: -0.0000

Data Index: 317136 (The Pile)

Max Activating Token Index: 72

Text #11

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6013. Min Act: -0.0000

Data Index: 1587831 (The Pile)

Max Activating Token Index: 190

Text #12

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.5676. Min Act: -0.0000

Data Index: 1756033 (The Pile)

Max Activating Token Index: 879

Text #13

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.5806. Min Act: -0.0000

Data Index: 975498 (The Pile)

Max Activating Token Index: 530

Text #14

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6133. Min Act: -0.0000

Data Index: 500861 (The Pile)

Max Activating Token Index: 610

Text #15

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6006. Min Act: -0.0000

Data Index: 641302 (The Pile)

Max Activating Token Index: 101

Text #16

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6324. Min Act: -0.0000

Data Index: 939963 (The Pile)

Max Activating Token Index: 36

Text #17

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.6054. Min Act: -0.0000

Data Index: 986063 (The Pile)

Max Activating Token Index: 568

Text #18

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.5737. Min Act: -0.0000

Data Index: 1890221 (The Pile)

Max Activating Token Index: 485

Text #19

Max Range: 1.0285. Min Range: -1.0285

Max Act: 0.5855. Min Act: -0.0000

Data Index: 357214 (The Pile)

Max Activating Token Index: 563