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

Dataset: The Pile

Neuron 3488 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.3010. Min Act: -0.0000

Data Index: 990575 (The Pile)

Max Activating Token Index: 745

Text #1

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.3245. Min Act: -0.0000

Data Index: 1205259 (The Pile)

Max Activating Token Index: 799

Text #2

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1071609 (The Pile)

Max Activating Token Index: 682

Text #3

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2544. Min Act: -0.0000

Data Index: 1712419 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1966. Min Act: -0.0000

Data Index: 1857260 (The Pile)

Max Activating Token Index: 387

Text #5

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2092. Min Act: -0.0000

Data Index: 324754 (The Pile)

Max Activating Token Index: 636

Text #6

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2085. Min Act: -0.0000

Data Index: 1846417 (The Pile)

Max Activating Token Index: 227

Text #7

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1731. Min Act: -0.0000

Data Index: 828152 (The Pile)

Max Activating Token Index: 474

Text #8

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2523. Min Act: -0.0000

Data Index: 1874788 (The Pile)

Max Activating Token Index: 869

Text #9

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1479. Min Act: -0.0000

Data Index: 198857 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1759. Min Act: -0.0000

Data Index: 1551371 (The Pile)

Max Activating Token Index: 354

Text #11

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.2057. Min Act: -0.0000

Data Index: 1659389 (The Pile)

Max Activating Token Index: 614

Text #12

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1095. Min Act: -0.0000

Data Index: 202612 (The Pile)

Max Activating Token Index: 966

Text #13

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1430. Min Act: -0.0000

Data Index: 244601 (The Pile)

Max Activating Token Index: 109

Text #14

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1775. Min Act: -0.0000

Data Index: 697129 (The Pile)

Max Activating Token Index: 447

Text #15

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1256. Min Act: -0.0000

Data Index: 682804 (The Pile)

Max Activating Token Index: 959

Text #16

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1368. Min Act: -0.0000

Data Index: 1665585 (The Pile)

Max Activating Token Index: 255

Text #17

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.0816. Min Act: -0.0000

Data Index: 921582 (The Pile)

Max Activating Token Index: 31

Text #18

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1100. Min Act: -0.0000

Data Index: 783476 (The Pile)

Max Activating Token Index: 161

Text #19

Max Range: 1.3245. Min Range: -1.3245

Max Act: 1.1316. Min Act: -0.0000

Data Index: 1408138 (The Pile)

Max Activating Token Index: 153