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

Dataset: The Pile

Neuron 4921 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: 1.1974. Min Range: -1.1974

Max Act: 1.1652. Min Act: -0.0000

Data Index: 1171734 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1974. Min Act: -0.0000

Data Index: 1546882 (The Pile)

Max Activating Token Index: 648

Text #2

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1760. Min Act: -0.0000

Data Index: 1819593 (The Pile)

Max Activating Token Index: 888

Text #3

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1625. Min Act: -0.0000

Data Index: 892774 (The Pile)

Max Activating Token Index: 644

Text #4

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1565. Min Act: -0.0000

Data Index: 1171182 (The Pile)

Max Activating Token Index: 268

Text #5

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1247. Min Act: -0.0000

Data Index: 774169 (The Pile)

Max Activating Token Index: 44

Text #6

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1034. Min Act: -0.0000

Data Index: 367930 (The Pile)

Max Activating Token Index: 531

Text #7

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1478. Min Act: -0.0000

Data Index: 993914 (The Pile)

Max Activating Token Index: 65

Text #8

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0183. Min Act: -0.0000

Data Index: 265020 (The Pile)

Max Activating Token Index: 795

Text #9

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0936. Min Act: -0.0000

Data Index: 511941 (The Pile)

Max Activating Token Index: 55

Text #10

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1210. Min Act: -0.0000

Data Index: 1755663 (The Pile)

Max Activating Token Index: 665

Text #11

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0772. Min Act: -0.0000

Data Index: 1588820 (The Pile)

Max Activating Token Index: 86

Text #12

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1344. Min Act: -0.0000

Data Index: 1482733 (The Pile)

Max Activating Token Index: 454

Text #13

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1106. Min Act: -0.0000

Data Index: 932804 (The Pile)

Max Activating Token Index: 35

Text #14

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0891. Min Act: -0.0000

Data Index: 879488 (The Pile)

Max Activating Token Index: 87

Text #15

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0826. Min Act: -0.0000

Data Index: 740269 (The Pile)

Max Activating Token Index: 150

Text #16

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0849. Min Act: -0.0000

Data Index: 1867499 (The Pile)

Max Activating Token Index: 225

Text #17

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0920. Min Act: -0.0000

Data Index: 1636362 (The Pile)

Max Activating Token Index: 748

Text #18

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.1013. Min Act: -0.0000

Data Index: 738086 (The Pile)

Max Activating Token Index: 462

Text #19

Max Range: 1.1974. Min Range: -1.1974

Max Act: 1.0370. Min Act: -0.0000

Data Index: 679043 (The Pile)

Max Activating Token Index: 85