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

Dataset: The Pile

Neuron 2200 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: 4.5689. Min Range: -4.5689

Max Act: 4.5689. Min Act: -0.0000

Data Index: 848336 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 4.5689. Min Range: -4.5689

Max Act: 4.4115. Min Act: -0.0000

Data Index: 1687837 (The Pile)

Max Activating Token Index: 334

Text #2

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.4932. Min Act: -0.0000

Data Index: 225189 (The Pile)

Max Activating Token Index: 659

Text #3

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.4275. Min Act: -0.0000

Data Index: 1799127 (The Pile)

Max Activating Token Index: 429

Text #4

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.3634. Min Act: -0.0000

Data Index: 1540647 (The Pile)

Max Activating Token Index: 610

Text #5

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.5104. Min Act: -0.0000

Data Index: 239847 (The Pile)

Max Activating Token Index: 804

Text #6

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.9316. Min Act: -0.0000

Data Index: 1446161 (The Pile)

Max Activating Token Index: 795

Text #7

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.1963. Min Act: -0.0000

Data Index: 1657474 (The Pile)

Max Activating Token Index: 850

Text #8

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.8671. Min Act: -0.0000

Data Index: 1314625 (The Pile)

Max Activating Token Index: 653

Text #9

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.3749. Min Act: -0.0000

Data Index: 1404067 (The Pile)

Max Activating Token Index: 552

Text #10

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.3392. Min Act: -0.0000

Data Index: 1795071 (The Pile)

Max Activating Token Index: 557

Text #11

Max Range: 4.5689. Min Range: -4.5689

Max Act: 3.0045. Min Act: -0.0000

Data Index: 1231852 (The Pile)

Max Activating Token Index: 368

Text #12

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.8750. Min Act: -0.0000

Data Index: 1940642 (The Pile)

Max Activating Token Index: 436

Text #13

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.8437. Min Act: -0.0000

Data Index: 978278 (The Pile)

Max Activating Token Index: 60

Text #14

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.9850. Min Act: -0.0000

Data Index: 1429920 (The Pile)

Max Activating Token Index: 381

Text #15

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.7640. Min Act: -0.0000

Data Index: 309600 (The Pile)

Max Activating Token Index: 602

Text #16

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.6783. Min Act: -0.0000

Data Index: 412035 (The Pile)

Max Activating Token Index: 792

Text #17

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.7574. Min Act: -0.0000

Data Index: 257731 (The Pile)

Max Activating Token Index: 949

Text #18

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.4692. Min Act: -0.0000

Data Index: 1592331 (The Pile)

Max Activating Token Index: 916

Text #19

Max Range: 4.5689. Min Range: -4.5689

Max Act: 2.8802. Min Act: -0.0000

Data Index: 725124 (The Pile)

Max Activating Token Index: 1014