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

Dataset: The Pile

Neuron 4361 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: 1.5719. Min Range: -1.5719

Max Act: 1.5719. Min Act: -0.0000

Data Index: 16363 (The Pile)

Max Activating Token Index: 650

Text #1

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.3599. Min Act: -0.0000

Data Index: 743732 (The Pile)

Max Activating Token Index: 921

Text #2

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.2470. Min Act: -0.0000

Data Index: 146559 (The Pile)

Max Activating Token Index: 368

Text #3

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.2773. Min Act: -0.0000

Data Index: 1470842 (The Pile)

Max Activating Token Index: 756

Text #4

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.2699. Min Act: -0.0000

Data Index: 1564345 (The Pile)

Max Activating Token Index: 787

Text #5

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.1327. Min Act: -0.0000

Data Index: 145747 (The Pile)

Max Activating Token Index: 61

Text #6

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0904. Min Act: -0.0000

Data Index: 996936 (The Pile)

Max Activating Token Index: 26

Text #7

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.1270. Min Act: -0.0000

Data Index: 440100 (The Pile)

Max Activating Token Index: 715

Text #8

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0883. Min Act: -0.0000

Data Index: 343666 (The Pile)

Max Activating Token Index: 283

Text #9

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0874. Min Act: -0.0000

Data Index: 937460 (The Pile)

Max Activating Token Index: 278

Text #10

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.1153. Min Act: -0.0000

Data Index: 171875 (The Pile)

Max Activating Token Index: 456

Text #11

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0900. Min Act: -0.0000

Data Index: 1049961 (The Pile)

Max Activating Token Index: 762

Text #12

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0713. Min Act: -0.0000

Data Index: 1460957 (The Pile)

Max Activating Token Index: 727

Text #13

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0333. Min Act: -0.0000

Data Index: 346471 (The Pile)

Max Activating Token Index: 940

Text #14

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0898. Min Act: -0.0000

Data Index: 757169 (The Pile)

Max Activating Token Index: 920

Text #15

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0631. Min Act: -0.0000

Data Index: 577888 (The Pile)

Max Activating Token Index: 278

Text #16

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0798. Min Act: -0.0000

Data Index: 910610 (The Pile)

Max Activating Token Index: 116

Text #17

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0829. Min Act: -0.0000

Data Index: 1687856 (The Pile)

Max Activating Token Index: 1003

Text #18

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0716. Min Act: -0.0000

Data Index: 1346654 (The Pile)

Max Activating Token Index: 406

Text #19

Max Range: 1.5719. Min Range: -1.5719

Max Act: 1.0958. Min Act: -0.0000

Data Index: 930127 (The Pile)

Max Activating Token Index: 783