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

Dataset: The Pile

Neuron 2990 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: 0.6635. Min Range: -0.6635

Max Act: 0.6635. Min Act: -0.0000

Data Index: 196363 (The Pile)

Max Activating Token Index: 463

Text #1

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.6590. Min Act: -0.0000

Data Index: 908086 (The Pile)

Max Activating Token Index: 118

Text #2

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.6115. Min Act: -0.0000

Data Index: 1763751 (The Pile)

Max Activating Token Index: 425

Text #3

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5968. Min Act: -0.0000

Data Index: 644453 (The Pile)

Max Activating Token Index: 349

Text #4

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5930. Min Act: -0.0000

Data Index: 1353536 (The Pile)

Max Activating Token Index: 957

Text #5

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5659. Min Act: -0.0000

Data Index: 517084 (The Pile)

Max Activating Token Index: 841

Text #6

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5700. Min Act: -0.0000

Data Index: 1771659 (The Pile)

Max Activating Token Index: 579

Text #7

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5833. Min Act: -0.0000

Data Index: 962436 (The Pile)

Max Activating Token Index: 357

Text #8

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5487. Min Act: -0.0000

Data Index: 1831100 (The Pile)

Max Activating Token Index: 62

Text #9

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5795. Min Act: -0.0000

Data Index: 1992222 (The Pile)

Max Activating Token Index: 717

Text #10

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5810. Min Act: -0.0000

Data Index: 1326163 (The Pile)

Max Activating Token Index: 1005

Text #11

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.6098. Min Act: -0.0000

Data Index: 540544 (The Pile)

Max Activating Token Index: 568

Text #12

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5600. Min Act: -0.0000

Data Index: 633869 (The Pile)

Max Activating Token Index: 275

Text #13

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5849. Min Act: -0.0000

Data Index: 585566 (The Pile)

Max Activating Token Index: 414

Text #14

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5680. Min Act: -0.0000

Data Index: 1333586 (The Pile)

Max Activating Token Index: 737

Text #15

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5680. Min Act: -0.0000

Data Index: 960898 (The Pile)

Max Activating Token Index: 166

Text #16

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5609. Min Act: -0.0000

Data Index: 682694 (The Pile)

Max Activating Token Index: 833

Text #17

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5228. Min Act: -0.0000

Data Index: 924793 (The Pile)

Max Activating Token Index: 126

Text #18

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5615. Min Act: -0.0000

Data Index: 1878872 (The Pile)

Max Activating Token Index: 994

Text #19

Max Range: 0.6635. Min Range: -0.6635

Max Act: 0.5987. Min Act: -0.0000

Data Index: 1434785 (The Pile)

Max Activating Token Index: 250