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

Dataset: The Pile

Neuron 2058 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6281. Min Act: -0.0000

Data Index: 422396 (The Pile)

Max Activating Token Index: 961

Text #1

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5698. Min Act: -0.0000

Data Index: 872238 (The Pile)

Max Activating Token Index: 738

Text #2

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.6689. Min Act: 0.0000

Data Index: 1686713 (The Pile)

Max Activating Token Index: 193

Text #3

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5458. Min Act: -0.0000

Data Index: 1238762 (The Pile)

Max Activating Token Index: 842

Text #4

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5648. Min Act: 0.0000

Data Index: 1868362 (The Pile)

Max Activating Token Index: 129

Text #5

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5176. Min Act: -0.0000

Data Index: 1622461 (The Pile)

Max Activating Token Index: 543

Text #6

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5593. Min Act: -0.0000

Data Index: 1554084 (The Pile)

Max Activating Token Index: 34

Text #7

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4977. Min Act: -0.0000

Data Index: 1794598 (The Pile)

Max Activating Token Index: 122

Text #8

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5065. Min Act: -0.0000

Data Index: 932434 (The Pile)

Max Activating Token Index: 185

Text #9

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5083. Min Act: -0.0000

Data Index: 111093 (The Pile)

Max Activating Token Index: 933

Text #10

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4737. Min Act: -0.0000

Data Index: 689429 (The Pile)

Max Activating Token Index: 484

Text #11

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.5128. Min Act: -0.0000

Data Index: 1915927 (The Pile)

Max Activating Token Index: 877

Text #12

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4778. Min Act: -0.0000

Data Index: 1208764 (The Pile)

Max Activating Token Index: 91

Text #13

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4916. Min Act: -0.0000

Data Index: 1821781 (The Pile)

Max Activating Token Index: 745

Text #14

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4802. Min Act: -0.0000

Data Index: 1057480 (The Pile)

Max Activating Token Index: 219

Text #15

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4769. Min Act: -0.0000

Data Index: 1934491 (The Pile)

Max Activating Token Index: 78

Text #16

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4776. Min Act: -0.0000

Data Index: 1029631 (The Pile)

Max Activating Token Index: 290

Text #17

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4684. Min Act: -0.0000

Data Index: 32876 (The Pile)

Max Activating Token Index: 283

Text #18

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4831. Min Act: -0.0000

Data Index: 536785 (The Pile)

Max Activating Token Index: 160

Text #19

Max Range: 0.6689. Min Range: -0.6689

Max Act: 0.4606. Min Act: -0.0000

Data Index: 512341 (The Pile)

Max Activating Token Index: 615