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

Dataset: The Pile

Neuron 3177 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: 0.9841. Min Range: -0.9841

Max Act: 0.9841. Min Act: -0.0000

Data Index: 886069 (The Pile)

Max Activating Token Index: 381

Text #1

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.8529. Min Act: -0.0000

Data Index: 1066067 (The Pile)

Max Activating Token Index: 897

Text #2

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.7565. Min Act: -0.0000

Data Index: 1085197 (The Pile)

Max Activating Token Index: 503

Text #3

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6811. Min Act: -0.0000

Data Index: 1452632 (The Pile)

Max Activating Token Index: 508

Text #4

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6149. Min Act: -0.0000

Data Index: 1743957 (The Pile)

Max Activating Token Index: 494

Text #5

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6667. Min Act: -0.0000

Data Index: 580600 (The Pile)

Max Activating Token Index: 530

Text #6

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6719. Min Act: -0.0000

Data Index: 1651759 (The Pile)

Max Activating Token Index: 228

Text #7

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6064. Min Act: -0.0000

Data Index: 812554 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5785. Min Act: -0.0000

Data Index: 1813046 (The Pile)

Max Activating Token Index: 441

Text #9

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6165. Min Act: -0.0000

Data Index: 1574471 (The Pile)

Max Activating Token Index: 510

Text #10

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6311. Min Act: -0.0000

Data Index: 1958749 (The Pile)

Max Activating Token Index: 283

Text #11

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1345316 (The Pile)

Max Activating Token Index: 874

Text #12

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6035. Min Act: -0.0000

Data Index: 319485 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5667. Min Act: -0.0000

Data Index: 935378 (The Pile)

Max Activating Token Index: 675

Text #14

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.6126. Min Act: -0.0000

Data Index: 547162 (The Pile)

Max Activating Token Index: 812

Text #15

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5856. Min Act: -0.0000

Data Index: 697334 (The Pile)

Max Activating Token Index: 582

Text #16

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5408. Min Act: -0.0000

Data Index: 1833947 (The Pile)

Max Activating Token Index: 730

Text #17

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5758. Min Act: -0.0000

Data Index: 590196 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5543. Min Act: -0.0000

Data Index: 827041 (The Pile)

Max Activating Token Index: 837

Text #19

Max Range: 0.9841. Min Range: -0.9841

Max Act: 0.5740. Min Act: -0.0000

Data Index: 1765366 (The Pile)

Max Activating Token Index: 975