Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 1873 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5930. Min Act: -0.0001

Data Index: 1525611 (The Pile)

Max Activating Token Index: 1019

Text #1

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6023. Min Act: -0.0000

Data Index: 158712 (The Pile)

Max Activating Token Index: 462

Text #2

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1102362 (The Pile)

Max Activating Token Index: 330

Text #3

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5824. Min Act: -0.0000

Data Index: 1808898 (The Pile)

Max Activating Token Index: 387

Text #4

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1131144 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5375. Min Act: -0.0000

Data Index: 236636 (The Pile)

Max Activating Token Index: 377

Text #6

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.6246. Min Act: -0.0000

Data Index: 1674889 (The Pile)

Max Activating Token Index: 606

Text #7

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5072. Min Act: -0.0000

Data Index: 1301321 (The Pile)

Max Activating Token Index: 541

Text #8

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5438. Min Act: -0.0000

Data Index: 1041947 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5807. Min Act: -0.0001

Data Index: 606363 (The Pile)

Max Activating Token Index: 976

Text #10

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5416. Min Act: -0.0000

Data Index: 1333561 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5181. Min Act: -0.0000

Data Index: 975813 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5309. Min Act: -0.0000

Data Index: 1403125 (The Pile)

Max Activating Token Index: 1002

Text #13

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5158. Min Act: -0.0000

Data Index: 870683 (The Pile)

Max Activating Token Index: 979

Text #14

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5572. Min Act: -0.0000

Data Index: 188549 (The Pile)

Max Activating Token Index: 275

Text #15

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.4727. Min Act: -0.0000

Data Index: 436148 (The Pile)

Max Activating Token Index: 750

Text #16

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5420. Min Act: -0.0000

Data Index: 452171 (The Pile)

Max Activating Token Index: 594

Text #17

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5166. Min Act: -0.0000

Data Index: 1190032 (The Pile)

Max Activating Token Index: 154

Text #18

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5330. Min Act: -0.0001

Data Index: 458682 (The Pile)

Max Activating Token Index: 815

Text #19

Max Range: 0.6246. Min Range: -0.6246

Max Act: 0.5056. Min Act: -0.0000

Data Index: 358035 (The Pile)

Max Activating Token Index: 297