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

Dataset: The Pile

Neuron 3765 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: 0.1371. Min Range: -0.1371

Max Act: 0.1371. Min Act: -0.0000

Data Index: 360204 (The Pile)

Max Activating Token Index: 904

Text #1

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1184. Min Act: -0.0000

Data Index: 821865 (The Pile)

Max Activating Token Index: 469

Text #2

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1121. Min Act: -0.0000

Data Index: 1627974 (The Pile)

Max Activating Token Index: 271

Text #3

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1084. Min Act: -0.0000

Data Index: 1846846 (The Pile)

Max Activating Token Index: 688

Text #4

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1111. Min Act: -0.0000

Data Index: 452718 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1131. Min Act: -0.0000

Data Index: 495963 (The Pile)

Max Activating Token Index: 304

Text #6

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1058. Min Act: -0.0000

Data Index: 500471 (The Pile)

Max Activating Token Index: 575

Text #7

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1067. Min Act: -0.0000

Data Index: 107909 (The Pile)

Max Activating Token Index: 543

Text #8

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0986. Min Act: -0.0000

Data Index: 203672 (The Pile)

Max Activating Token Index: 524

Text #9

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1022. Min Act: -0.0000

Data Index: 758115 (The Pile)

Max Activating Token Index: 496

Text #10

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0974. Min Act: -0.0000

Data Index: 388434 (The Pile)

Max Activating Token Index: 624

Text #11

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.1020. Min Act: -0.0000

Data Index: 799954 (The Pile)

Max Activating Token Index: 383

Text #12

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0948. Min Act: -0.0000

Data Index: 1891890 (The Pile)

Max Activating Token Index: 692

Text #13

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0966. Min Act: -0.0000

Data Index: 264728 (The Pile)

Max Activating Token Index: 71

Text #14

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0937. Min Act: -0.0000

Data Index: 1355203 (The Pile)

Max Activating Token Index: 682

Text #15

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0851. Min Act: -0.0000

Data Index: 1661345 (The Pile)

Max Activating Token Index: 168

Text #16

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0888. Min Act: -0.0000

Data Index: 1883829 (The Pile)

Max Activating Token Index: 164

Text #17

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0858. Min Act: -0.0000

Data Index: 467051 (The Pile)

Max Activating Token Index: 95

Text #18

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0963. Min Act: -0.0000

Data Index: 1545810 (The Pile)

Max Activating Token Index: 676

Text #19

Max Range: 0.1371. Min Range: -0.1371

Max Act: 0.0855. Min Act: -0.0000

Data Index: 1972801 (The Pile)

Max Activating Token Index: 370