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

Dataset: The Pile

Neuron 1890 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: 0.6217. Min Range: -0.6217

Max Act: 0.6217. Min Act: -0.0000

Data Index: 1655900 (The Pile)

Max Activating Token Index: 935

Text #1

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4875. Min Act: -0.0000

Data Index: 728805 (The Pile)

Max Activating Token Index: 1023

Text #2

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4505. Min Act: -0.0000

Data Index: 174544 (The Pile)

Max Activating Token Index: 485

Text #3

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4666. Min Act: -0.0000

Data Index: 977527 (The Pile)

Max Activating Token Index: 711

Text #4

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4366. Min Act: -0.0000

Data Index: 1753158 (The Pile)

Max Activating Token Index: 446

Text #5

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4153. Min Act: -0.0000

Data Index: 1676864 (The Pile)

Max Activating Token Index: 623

Text #6

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3717. Min Act: -0.0000

Data Index: 640333 (The Pile)

Max Activating Token Index: 460

Text #7

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3966. Min Act: -0.0000

Data Index: 909876 (The Pile)

Max Activating Token Index: 423

Text #8

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3845. Min Act: -0.0000

Data Index: 494730 (The Pile)

Max Activating Token Index: 196

Text #9

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.4036. Min Act: -0.0000

Data Index: 920178 (The Pile)

Max Activating Token Index: 131

Text #10

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3734. Min Act: -0.0000

Data Index: 1891506 (The Pile)

Max Activating Token Index: 6

Text #11

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3425. Min Act: -0.0000

Data Index: 626405 (The Pile)

Max Activating Token Index: 832

Text #12

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3700. Min Act: -0.0000

Data Index: 880759 (The Pile)

Max Activating Token Index: 732

Text #13

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3672. Min Act: -0.0000

Data Index: 1314151 (The Pile)

Max Activating Token Index: 338

Text #14

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3556. Min Act: -0.0000

Data Index: 82437 (The Pile)

Max Activating Token Index: 62

Text #15

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3682. Min Act: -0.0000

Data Index: 705798 (The Pile)

Max Activating Token Index: 54

Text #16

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3713. Min Act: -0.0000

Data Index: 1773256 (The Pile)

Max Activating Token Index: 722

Text #17

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3521. Min Act: -0.0000

Data Index: 686926 (The Pile)

Max Activating Token Index: 716

Text #18

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3666. Min Act: -0.0000

Data Index: 319101 (The Pile)

Max Activating Token Index: 903

Text #19

Max Range: 0.6217. Min Range: -0.6217

Max Act: 0.3644. Min Act: -0.0000

Data Index: 618387 (The Pile)

Max Activating Token Index: 672