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

Dataset: The Pile

Neuron 2784 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.6930. Min Act: -0.0000

Data Index: 1984826 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.5189. Min Act: -0.0000

Data Index: 278782 (The Pile)

Max Activating Token Index: 228

Text #2

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.4096. Min Act: -0.0000

Data Index: 1027701 (The Pile)

Max Activating Token Index: 33

Text #3

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3746. Min Act: -0.0000

Data Index: 136977 (The Pile)

Max Activating Token Index: 778

Text #4

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3691. Min Act: -0.0000

Data Index: 452613 (The Pile)

Max Activating Token Index: 604

Text #5

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3314. Min Act: -0.0000

Data Index: 1006280 (The Pile)

Max Activating Token Index: 529

Text #6

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3311. Min Act: -0.0000

Data Index: 342045 (The Pile)

Max Activating Token Index: 285

Text #7

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.2663. Min Act: -0.0000

Data Index: 1566201 (The Pile)

Max Activating Token Index: 646

Text #8

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3366. Min Act: -0.0000

Data Index: 453511 (The Pile)

Max Activating Token Index: 349

Text #9

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3543. Min Act: -0.0000

Data Index: 1910218 (The Pile)

Max Activating Token Index: 527

Text #10

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3221. Min Act: -0.0000

Data Index: 1069960 (The Pile)

Max Activating Token Index: 782

Text #11

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3560. Min Act: -0.0000

Data Index: 1433359 (The Pile)

Max Activating Token Index: 592

Text #12

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3108. Min Act: -0.0000

Data Index: 475510 (The Pile)

Max Activating Token Index: 285

Text #13

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.2977. Min Act: -0.0000

Data Index: 1062915 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.2896. Min Act: -0.0000

Data Index: 1172074 (The Pile)

Max Activating Token Index: 444

Text #15

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3048. Min Act: -0.0000

Data Index: 197603 (The Pile)

Max Activating Token Index: 962

Text #16

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3007. Min Act: -0.0000

Data Index: 1036685 (The Pile)

Max Activating Token Index: 145

Text #17

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3097. Min Act: -0.0000

Data Index: 1430401 (The Pile)

Max Activating Token Index: 184

Text #18

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3016. Min Act: -0.0000

Data Index: 1381797 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 0.6930. Min Range: -0.6930

Max Act: 0.3175. Min Act: -0.0000

Data Index: 521637 (The Pile)

Max Activating Token Index: 299