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

Dataset: The Pile

Neuron 1470 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.8130. Min Act: -0.0000

Data Index: 272339 (The Pile)

Max Activating Token Index: 176

Text #1

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.6003. Min Act: -0.0000

Data Index: 907766 (The Pile)

Max Activating Token Index: 420

Text #2

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5648. Min Act: -0.0000

Data Index: 123332 (The Pile)

Max Activating Token Index: 573

Text #3

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5910. Min Act: -0.0000

Data Index: 1622437 (The Pile)

Max Activating Token Index: 814

Text #4

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5493. Min Act: -0.0000

Data Index: 1402212 (The Pile)

Max Activating Token Index: 75

Text #5

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5378. Min Act: -0.0000

Data Index: 1401796 (The Pile)

Max Activating Token Index: 547

Text #6

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.6801. Min Act: -0.0000

Data Index: 1369978 (The Pile)

Max Activating Token Index: 808

Text #7

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.6330. Min Act: -0.0000

Data Index: 1837148 (The Pile)

Max Activating Token Index: 1009

Text #8

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5200. Min Act: -0.0000

Data Index: 7376 (The Pile)

Max Activating Token Index: 46

Text #9

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5513. Min Act: -0.0000

Data Index: 597742 (The Pile)

Max Activating Token Index: 865

Text #10

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.4809. Min Act: -0.0000

Data Index: 1720865 (The Pile)

Max Activating Token Index: 91

Text #11

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.4961. Min Act: -0.0000

Data Index: 1511387 (The Pile)

Max Activating Token Index: 827

Text #12

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5107. Min Act: -0.0000

Data Index: 1048571 (The Pile)

Max Activating Token Index: 158

Text #13

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.4721. Min Act: -0.0000

Data Index: 397603 (The Pile)

Max Activating Token Index: 199

Text #14

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5733. Min Act: -0.0000

Data Index: 758038 (The Pile)

Max Activating Token Index: 816

Text #15

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5299. Min Act: -0.0000

Data Index: 1218920 (The Pile)

Max Activating Token Index: 16

Text #16

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5105. Min Act: -0.0000

Data Index: 1918029 (The Pile)

Max Activating Token Index: 508

Text #17

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.4768. Min Act: -0.0000

Data Index: 355402 (The Pile)

Max Activating Token Index: 760

Text #18

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5090. Min Act: -0.0000

Data Index: 734849 (The Pile)

Max Activating Token Index: 349

Text #19

Max Range: 0.8130. Min Range: -0.8130

Max Act: 0.5406. Min Act: -0.0000

Data Index: 1581174 (The Pile)

Max Activating Token Index: 980