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

Dataset: The Pile

Neuron 455 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.2410. Min Act: -0.0000

Data Index: 1060628 (The Pile)

Max Activating Token Index: 936

Text #1

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1846. Min Act: -0.0000

Data Index: 554209 (The Pile)

Max Activating Token Index: 89

Text #2

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1665. Min Act: -0.0000

Data Index: 1368573 (The Pile)

Max Activating Token Index: 94

Text #3

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1300716 (The Pile)

Max Activating Token Index: 995

Text #4

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1173. Min Act: -0.0000

Data Index: 349109 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1218. Min Act: -0.0000

Data Index: 1598177 (The Pile)

Max Activating Token Index: 122

Text #6

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1229. Min Act: -0.0000

Data Index: 971081 (The Pile)

Max Activating Token Index: 45

Text #7

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1108. Min Act: -0.0000

Data Index: 1179203 (The Pile)

Max Activating Token Index: 411

Text #8

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1025. Min Act: -0.0000

Data Index: 1751252 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1091. Min Act: -0.0000

Data Index: 704254 (The Pile)

Max Activating Token Index: 806

Text #10

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1097. Min Act: -0.0000

Data Index: 1046206 (The Pile)

Max Activating Token Index: 890

Text #11

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1245. Min Act: -0.0000

Data Index: 343261 (The Pile)

Max Activating Token Index: 49

Text #12

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1201. Min Act: -0.0000

Data Index: 656991 (The Pile)

Max Activating Token Index: 444

Text #13

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1127. Min Act: -0.0000

Data Index: 208542 (The Pile)

Max Activating Token Index: 837

Text #14

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1022. Min Act: -0.0000

Data Index: 561440 (The Pile)

Max Activating Token Index: 185

Text #15

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1088. Min Act: -0.0000

Data Index: 1296580 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1140. Min Act: -0.0000

Data Index: 480579 (The Pile)

Max Activating Token Index: 605

Text #17

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1067. Min Act: -0.0000

Data Index: 841128 (The Pile)

Max Activating Token Index: 400

Text #18

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.1193. Min Act: -0.0000

Data Index: 79343 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 0.2410. Min Range: -0.2410

Max Act: 0.0929. Min Act: -0.0000

Data Index: 1344888 (The Pile)

Max Activating Token Index: 648