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

Dataset: The Pile

Neuron 3730 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: 0.1181. Min Range: -0.1181

Max Act: 0.1181. Min Act: -0.0000

Data Index: 718605 (The Pile)

Max Activating Token Index: 755

Text #1

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1011. Min Act: -0.0000

Data Index: 605603 (The Pile)

Max Activating Token Index: 1007

Text #2

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.1019. Min Act: -0.0000

Data Index: 216948 (The Pile)

Max Activating Token Index: 840

Text #3

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0935. Min Act: -0.0000

Data Index: 468110 (The Pile)

Max Activating Token Index: 780

Text #4

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0991. Min Act: -0.0000

Data Index: 1672228 (The Pile)

Max Activating Token Index: 167

Text #5

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0957. Min Act: -0.0000

Data Index: 458372 (The Pile)

Max Activating Token Index: 763

Text #6

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0964. Min Act: -0.0000

Data Index: 888195 (The Pile)

Max Activating Token Index: 229

Text #7

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0917. Min Act: -0.0000

Data Index: 1447779 (The Pile)

Max Activating Token Index: 813

Text #8

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0909. Min Act: -0.0000

Data Index: 1348503 (The Pile)

Max Activating Token Index: 893

Text #9

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0860. Min Act: -0.0001

Data Index: 1445715 (The Pile)

Max Activating Token Index: 333

Text #10

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0870. Min Act: -0.0000

Data Index: 1574406 (The Pile)

Max Activating Token Index: 843

Text #11

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0907. Min Act: -0.0000

Data Index: 923014 (The Pile)

Max Activating Token Index: 848

Text #12

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0942. Min Act: -0.0000

Data Index: 333556 (The Pile)

Max Activating Token Index: 412

Text #13

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0895. Min Act: -0.0000

Data Index: 1717546 (The Pile)

Max Activating Token Index: 386

Text #14

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0891. Min Act: -0.0000

Data Index: 399478 (The Pile)

Max Activating Token Index: 434

Text #15

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1618566 (The Pile)

Max Activating Token Index: 256

Text #16

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0904. Min Act: -0.0000

Data Index: 276472 (The Pile)

Max Activating Token Index: 117

Text #17

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0857. Min Act: -0.0000

Data Index: 848800 (The Pile)

Max Activating Token Index: 360

Text #18

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0793. Min Act: -0.0000

Data Index: 1812231 (The Pile)

Max Activating Token Index: 822

Text #19

Max Range: 0.1181. Min Range: -0.1181

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1645312 (The Pile)

Max Activating Token Index: 844