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

Dataset: The Pile

Neuron 3487 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2412. Min Act: -0.0000

Data Index: 1265451 (The Pile)

Max Activating Token Index: 526

Text #1

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2284. Min Act: -0.0000

Data Index: 1044910 (The Pile)

Max Activating Token Index: 156

Text #2

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1984. Min Act: -0.0000

Data Index: 307773 (The Pile)

Max Activating Token Index: 233

Text #3

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2017. Min Act: -0.0000

Data Index: 340584 (The Pile)

Max Activating Token Index: 191

Text #4

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1722. Min Act: -0.0000

Data Index: 1631075 (The Pile)

Max Activating Token Index: 413

Text #5

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1948. Min Act: -0.0000

Data Index: 1915214 (The Pile)

Max Activating Token Index: 497

Text #6

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1749. Min Act: -0.0000

Data Index: 400703 (The Pile)

Max Activating Token Index: 419

Text #7

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1727. Min Act: -0.0000

Data Index: 836584 (The Pile)

Max Activating Token Index: 377

Text #8

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2051. Min Act: -0.0000

Data Index: 232363 (The Pile)

Max Activating Token Index: 1004

Text #9

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.2022. Min Act: -0.0000

Data Index: 1430115 (The Pile)

Max Activating Token Index: 209

Text #10

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1772. Min Act: -0.0000

Data Index: 1878991 (The Pile)

Max Activating Token Index: 647

Text #11

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1843. Min Act: -0.0000

Data Index: 852597 (The Pile)

Max Activating Token Index: 378

Text #12

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1775. Min Act: -0.0000

Data Index: 86331 (The Pile)

Max Activating Token Index: 501

Text #13

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1706. Min Act: -0.0000

Data Index: 1374696 (The Pile)

Max Activating Token Index: 617

Text #14

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1786. Min Act: -0.0000

Data Index: 674590 (The Pile)

Max Activating Token Index: 531

Text #15

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1821. Min Act: -0.0000

Data Index: 1147373 (The Pile)

Max Activating Token Index: 377

Text #16

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1694. Min Act: -0.0000

Data Index: 369542 (The Pile)

Max Activating Token Index: 716

Text #17

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1674. Min Act: -0.0000

Data Index: 1281775 (The Pile)

Max Activating Token Index: 731

Text #18

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1718. Min Act: -0.0000

Data Index: 1772871 (The Pile)

Max Activating Token Index: 734

Text #19

Max Range: 0.2412. Min Range: -0.2412

Max Act: 0.1659. Min Act: -0.0000

Data Index: 892359 (The Pile)

Max Activating Token Index: 241