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

Dataset: The Pile

Neuron 3698 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.6806. Min Act: -0.0000

Data Index: 1131806 (The Pile)

Max Activating Token Index: 193

Text #1

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0905. Min Act: -0.0000

Data Index: 1170035 (The Pile)

Max Activating Token Index: 894

Text #2

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0712. Min Act: -0.0000

Data Index: 682446 (The Pile)

Max Activating Token Index: 563

Text #3

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1324. Min Act: -0.0000

Data Index: 1888368 (The Pile)

Max Activating Token Index: 641

Text #4

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0529. Min Act: -0.0000

Data Index: 572582 (The Pile)

Max Activating Token Index: 213

Text #5

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0660. Min Act: -0.0000

Data Index: 1622748 (The Pile)

Max Activating Token Index: 10

Text #6

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.1077. Min Act: -0.0000

Data Index: 104945 (The Pile)

Max Activating Token Index: 420

Text #7

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.2400. Min Act: -0.0000

Data Index: 763437 (The Pile)

Max Activating Token Index: 1018

Text #8

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9692. Min Act: -0.0000

Data Index: 1874905 (The Pile)

Max Activating Token Index: 692

Text #9

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0714. Min Act: -0.0000

Data Index: 977801 (The Pile)

Max Activating Token Index: 612

Text #10

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0614. Min Act: -0.0000

Data Index: 1534139 (The Pile)

Max Activating Token Index: 74

Text #11

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9646. Min Act: -0.0000

Data Index: 1364123 (The Pile)

Max Activating Token Index: 408

Text #12

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9554. Min Act: -0.0000

Data Index: 988955 (The Pile)

Max Activating Token Index: 300

Text #13

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9941. Min Act: -0.0000

Data Index: 1523666 (The Pile)

Max Activating Token Index: 637

Text #14

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0913. Min Act: -0.0000

Data Index: 1031989 (The Pile)

Max Activating Token Index: 840

Text #15

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0970. Min Act: -0.0000

Data Index: 612793 (The Pile)

Max Activating Token Index: 928

Text #16

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9209. Min Act: -0.0000

Data Index: 640750 (The Pile)

Max Activating Token Index: 709

Text #17

Max Range: 1.6806. Min Range: -1.6806

Max Act: 1.0974. Min Act: -0.0000

Data Index: 1360169 (The Pile)

Max Activating Token Index: 11

Text #18

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9632. Min Act: -0.0000

Data Index: 1714980 (The Pile)

Max Activating Token Index: 145

Text #19

Max Range: 1.6806. Min Range: -1.6806

Max Act: 0.9561. Min Act: -0.0000

Data Index: 934262 (The Pile)

Max Activating Token Index: 70