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

Dataset: The Pile

Neuron 4407 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: 0.9558. Min Range: -0.9558

Max Act: 0.9558. Min Act: -0.0000

Data Index: 1240593 (The Pile)

Max Activating Token Index: 122

Text #1

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.7282. Min Act: -0.0000

Data Index: 604769 (The Pile)

Max Activating Token Index: 170

Text #2

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6752. Min Act: -0.0000

Data Index: 1634581 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6779. Min Act: -0.0000

Data Index: 44959 (The Pile)

Max Activating Token Index: 976

Text #4

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6522. Min Act: -0.0000

Data Index: 595018 (The Pile)

Max Activating Token Index: 508

Text #5

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6133. Min Act: -0.0000

Data Index: 1584044 (The Pile)

Max Activating Token Index: 457

Text #6

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6183. Min Act: -0.0000

Data Index: 1694500 (The Pile)

Max Activating Token Index: 738

Text #7

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5612. Min Act: -0.0000

Data Index: 1248837 (The Pile)

Max Activating Token Index: 384

Text #8

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5902. Min Act: -0.0000

Data Index: 669797 (The Pile)

Max Activating Token Index: 274

Text #9

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5736. Min Act: -0.0000

Data Index: 820649 (The Pile)

Max Activating Token Index: 869

Text #10

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6048. Min Act: -0.0000

Data Index: 401488 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6261. Min Act: -0.0000

Data Index: 228209 (The Pile)

Max Activating Token Index: 873

Text #12

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5760. Min Act: -0.0000

Data Index: 1259461 (The Pile)

Max Activating Token Index: 344

Text #13

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5948. Min Act: -0.0000

Data Index: 1159778 (The Pile)

Max Activating Token Index: 806

Text #14

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5893. Min Act: -0.0000

Data Index: 904001 (The Pile)

Max Activating Token Index: 661

Text #15

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5828. Min Act: -0.0000

Data Index: 1656810 (The Pile)

Max Activating Token Index: 494

Text #16

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5803. Min Act: -0.0000

Data Index: 360587 (The Pile)

Max Activating Token Index: 638

Text #17

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5699. Min Act: -0.0000

Data Index: 125004 (The Pile)

Max Activating Token Index: 839

Text #18

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.6164. Min Act: -0.0000

Data Index: 1187660 (The Pile)

Max Activating Token Index: 94

Text #19

Max Range: 0.9558. Min Range: -0.9558

Max Act: 0.5950. Min Act: -0.0001

Data Index: 1690465 (The Pile)

Max Activating Token Index: 632