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

Dataset: The Pile

Neuron 1266 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6895. Min Act: -0.0000

Data Index: 270828 (The Pile)

Max Activating Token Index: 369

Text #1

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6542. Min Act: -0.0000

Data Index: 1994111 (The Pile)

Max Activating Token Index: 472

Text #2

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6430. Min Act: -0.0000

Data Index: 1091917 (The Pile)

Max Activating Token Index: 958

Text #3

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6449. Min Act: -0.0000

Data Index: 847751 (The Pile)

Max Activating Token Index: 776

Text #4

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6103. Min Act: -0.0000

Data Index: 145535 (The Pile)

Max Activating Token Index: 783

Text #5

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5867. Min Act: -0.0000

Data Index: 717708 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6240. Min Act: -0.0000

Data Index: 1145406 (The Pile)

Max Activating Token Index: 872

Text #7

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6814. Min Act: -0.0000

Data Index: 1193834 (The Pile)

Max Activating Token Index: 966

Text #8

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5850. Min Act: -0.0000

Data Index: 1709470 (The Pile)

Max Activating Token Index: 734

Text #9

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5821. Min Act: -0.0000

Data Index: 1556843 (The Pile)

Max Activating Token Index: 263

Text #10

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6075. Min Act: -0.0000

Data Index: 1924848 (The Pile)

Max Activating Token Index: 1007

Text #11

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5907. Min Act: -0.0000

Data Index: 1708472 (The Pile)

Max Activating Token Index: 298

Text #12

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5470. Min Act: -0.0000

Data Index: 1859811 (The Pile)

Max Activating Token Index: 675

Text #13

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5926. Min Act: -0.0000

Data Index: 1810891 (The Pile)

Max Activating Token Index: 850

Text #14

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5094. Min Act: -0.0000

Data Index: 964815 (The Pile)

Max Activating Token Index: 953

Text #15

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.6223. Min Act: -0.0000

Data Index: 1635523 (The Pile)

Max Activating Token Index: 704

Text #16

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5748. Min Act: -0.0000

Data Index: 1560700 (The Pile)

Max Activating Token Index: 969

Text #17

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5753. Min Act: -0.0000

Data Index: 922356 (The Pile)

Max Activating Token Index: 483

Text #18

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5986. Min Act: -0.0000

Data Index: 1430614 (The Pile)

Max Activating Token Index: 936

Text #19

Max Range: 0.6895. Min Range: -0.6895

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1388680 (The Pile)

Max Activating Token Index: 875