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

Dataset: The Pile

Neuron 3302 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.1738. Min Act: -0.0000

Data Index: 1576505 (The Pile)

Max Activating Token Index: 447

Text #1

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0985. Min Act: -0.0000

Data Index: 1319581 (The Pile)

Max Activating Token Index: 106

Text #2

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1891277 (The Pile)

Max Activating Token Index: 915

Text #3

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0842. Min Act: -0.0000

Data Index: 1790178 (The Pile)

Max Activating Token Index: 276

Text #4

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0746. Min Act: -0.0000

Data Index: 309793 (The Pile)

Max Activating Token Index: 744

Text #5

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0762. Min Act: -0.0000

Data Index: 3548 (The Pile)

Max Activating Token Index: 365

Text #6

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0789. Min Act: -0.0000

Data Index: 1799546 (The Pile)

Max Activating Token Index: 746

Text #7

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0785. Min Act: -0.0000

Data Index: 1498364 (The Pile)

Max Activating Token Index: 804

Text #8

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0733. Min Act: -0.0000

Data Index: 1982950 (The Pile)

Max Activating Token Index: 685

Text #9

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0774. Min Act: -0.0000

Data Index: 1214495 (The Pile)

Max Activating Token Index: 336

Text #10

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0692. Min Act: -0.0000

Data Index: 473698 (The Pile)

Max Activating Token Index: 783

Text #11

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0692. Min Act: -0.0000

Data Index: 1653066 (The Pile)

Max Activating Token Index: 782

Text #12

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0602. Min Act: -0.0000

Data Index: 1536407 (The Pile)

Max Activating Token Index: 763

Text #13

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0655. Min Act: -0.0000

Data Index: 844466 (The Pile)

Max Activating Token Index: 1012

Text #14

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0684. Min Act: -0.0000

Data Index: 1172706 (The Pile)

Max Activating Token Index: 525

Text #15

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0743. Min Act: -0.0000

Data Index: 481800 (The Pile)

Max Activating Token Index: 349

Text #16

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0640. Min Act: -0.0000

Data Index: 1418724 (The Pile)

Max Activating Token Index: 112

Text #17

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0711. Min Act: -0.0000

Data Index: 997719 (The Pile)

Max Activating Token Index: 623

Text #18

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0610. Min Act: -0.0000

Data Index: 1973237 (The Pile)

Max Activating Token Index: 503

Text #19

Max Range: 0.1738. Min Range: -0.1738

Max Act: 0.0621. Min Act: -0.0000

Data Index: 1235905 (The Pile)

Max Activating Token Index: 81