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

Dataset: The Pile

Neuron 1927 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.5008. Min Act: -0.0000

Data Index: 1172777 (The Pile)

Max Activating Token Index: 844

Text #1

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.1209. Min Act: -0.0000

Data Index: 1294950 (The Pile)

Max Activating Token Index: 257

Text #2

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.2088. Min Act: -0.0000

Data Index: 471412 (The Pile)

Max Activating Token Index: 802

Text #3

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.1329. Min Act: -0.0000

Data Index: 1081808 (The Pile)

Max Activating Token Index: 921

Text #4

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.2894. Min Act: -0.0000

Data Index: 1623381 (The Pile)

Max Activating Token Index: 815

Text #5

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.2697. Min Act: -0.0000

Data Index: 1486959 (The Pile)

Max Activating Token Index: 815

Text #6

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.1898. Min Act: -0.0000

Data Index: 1913584 (The Pile)

Max Activating Token Index: 482

Text #7

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.1081. Min Act: -0.0000

Data Index: 937841 (The Pile)

Max Activating Token Index: 316

Text #8

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0744. Min Act: -0.0000

Data Index: 1981343 (The Pile)

Max Activating Token Index: 281

Text #9

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.2602. Min Act: -0.0000

Data Index: 429868 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0511. Min Act: -0.0000

Data Index: 259727 (The Pile)

Max Activating Token Index: 999

Text #11

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.1848. Min Act: -0.0000

Data Index: 451918 (The Pile)

Max Activating Token Index: 668

Text #12

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0565. Min Act: -0.0000

Data Index: 147440 (The Pile)

Max Activating Token Index: 129

Text #13

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0977. Min Act: -0.0000

Data Index: 1334757 (The Pile)

Max Activating Token Index: 150

Text #14

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.1479. Min Act: -0.0000

Data Index: 1597972 (The Pile)

Max Activating Token Index: 818

Text #15

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0891. Min Act: -0.0000

Data Index: 1081915 (The Pile)

Max Activating Token Index: 949

Text #16

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0404. Min Act: -0.0000

Data Index: 28477 (The Pile)

Max Activating Token Index: 431

Text #17

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0055. Min Act: -0.0000

Data Index: 1114769 (The Pile)

Max Activating Token Index: 955

Text #18

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0442. Min Act: -0.0000

Data Index: 482777 (The Pile)

Max Activating Token Index: 838

Text #19

Max Range: 1.5008. Min Range: -1.5008

Max Act: 1.0124. Min Act: -0.0000

Data Index: 1560840 (The Pile)

Max Activating Token Index: 273