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

Dataset: The Pile

Neuron 3643 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: 0.7778. Min Range: -0.7778

Max Act: 0.7778. Min Act: -0.0000

Data Index: 1386014 (The Pile)

Max Activating Token Index: 118

Text #1

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.7125. Min Act: -0.0000

Data Index: 193140 (The Pile)

Max Activating Token Index: 849

Text #2

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6698. Min Act: -0.0000

Data Index: 678183 (The Pile)

Max Activating Token Index: 950

Text #3

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6838. Min Act: -0.0000

Data Index: 558584 (The Pile)

Max Activating Token Index: 395

Text #4

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5906. Min Act: -0.0000

Data Index: 1725282 (The Pile)

Max Activating Token Index: 830

Text #5

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5807. Min Act: -0.0000

Data Index: 802474 (The Pile)

Max Activating Token Index: 776

Text #6

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6111. Min Act: -0.0000

Data Index: 157938 (The Pile)

Max Activating Token Index: 715

Text #7

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6219. Min Act: -0.0000

Data Index: 1588766 (The Pile)

Max Activating Token Index: 262

Text #8

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6074. Min Act: -0.0000

Data Index: 1400680 (The Pile)

Max Activating Token Index: 464

Text #9

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6449. Min Act: -0.0000

Data Index: 313040 (The Pile)

Max Activating Token Index: 682

Text #10

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5889. Min Act: -0.0000

Data Index: 82037 (The Pile)

Max Activating Token Index: 958

Text #11

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1076934 (The Pile)

Max Activating Token Index: 278

Text #12

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5603. Min Act: -0.0000

Data Index: 1337278 (The Pile)

Max Activating Token Index: 691

Text #13

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5549. Min Act: -0.0000

Data Index: 877636 (The Pile)

Max Activating Token Index: 726

Text #14

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.6117. Min Act: -0.0000

Data Index: 598322 (The Pile)

Max Activating Token Index: 573

Text #15

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5914. Min Act: -0.0000

Data Index: 1220175 (The Pile)

Max Activating Token Index: 561

Text #16

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5538. Min Act: -0.0000

Data Index: 964696 (The Pile)

Max Activating Token Index: 253

Text #17

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5119. Min Act: -0.0000

Data Index: 749722 (The Pile)

Max Activating Token Index: 660

Text #18

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5634. Min Act: -0.0000

Data Index: 7094 (The Pile)

Max Activating Token Index: 764

Text #19

Max Range: 0.7778. Min Range: -0.7778

Max Act: 0.5807. Min Act: -0.0000

Data Index: 285794 (The Pile)

Max Activating Token Index: 688