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

Dataset: The Pile

Neuron 105 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: 0.6945. Min Range: -0.6945

Max Act: 0.6945. Min Act: -0.0000

Data Index: 1857064 (The Pile)

Max Activating Token Index: 352

Text #1

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6553. Min Act: -0.0000

Data Index: 867407 (The Pile)

Max Activating Token Index: 635

Text #2

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6259. Min Act: -0.0000

Data Index: 545654 (The Pile)

Max Activating Token Index: 953

Text #3

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6551. Min Act: -0.0000

Data Index: 1142410 (The Pile)

Max Activating Token Index: 719

Text #4

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5897. Min Act: -0.0000

Data Index: 826817 (The Pile)

Max Activating Token Index: 373

Text #5

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6061. Min Act: -0.0000

Data Index: 199234 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5459. Min Act: -0.0000

Data Index: 844158 (The Pile)

Max Activating Token Index: 607

Text #7

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5638. Min Act: -0.0000

Data Index: 1174762 (The Pile)

Max Activating Token Index: 29

Text #8

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.6085. Min Act: -0.0000

Data Index: 1234335 (The Pile)

Max Activating Token Index: 787

Text #9

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5870. Min Act: -0.0000

Data Index: 1594453 (The Pile)

Max Activating Token Index: 384

Text #10

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5394. Min Act: -0.0000

Data Index: 94104 (The Pile)

Max Activating Token Index: 81

Text #11

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5384. Min Act: -0.0000

Data Index: 840842 (The Pile)

Max Activating Token Index: 863

Text #12

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5633. Min Act: -0.0000

Data Index: 1573119 (The Pile)

Max Activating Token Index: 768

Text #13

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5434. Min Act: -0.0000

Data Index: 909080 (The Pile)

Max Activating Token Index: 890

Text #14

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5106. Min Act: -0.0000

Data Index: 1742848 (The Pile)

Max Activating Token Index: 865

Text #15

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5178. Min Act: -0.0000

Data Index: 1983667 (The Pile)

Max Activating Token Index: 1002

Text #16

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5361. Min Act: -0.0000

Data Index: 1969566 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5222. Min Act: -0.0000

Data Index: 1423604 (The Pile)

Max Activating Token Index: 1012

Text #18

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.5243. Min Act: -0.0000

Data Index: 192811 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.6945. Min Range: -0.6945

Max Act: 0.4687. Min Act: -0.0000

Data Index: 896596 (The Pile)

Max Activating Token Index: 655