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

Dataset: The Pile

Neuron 665 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: 1.7881. Min Range: -1.7881

Max Act: 1.5971. Min Act: -0.0000

Data Index: 843599 (The Pile)

Max Activating Token Index: 725

Text #1

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5642. Min Act: -0.0000

Data Index: 694610 (The Pile)

Max Activating Token Index: 197

Text #2

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5772. Min Act: -0.0000

Data Index: 1400768 (The Pile)

Max Activating Token Index: 556

Text #3

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.7881. Min Act: -0.0000

Data Index: 537166 (The Pile)

Max Activating Token Index: 278

Text #4

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6044. Min Act: -0.0000

Data Index: 1218068 (The Pile)

Max Activating Token Index: 422

Text #5

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6873. Min Act: -0.0000

Data Index: 1217959 (The Pile)

Max Activating Token Index: 29

Text #6

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5078. Min Act: -0.0000

Data Index: 1072394 (The Pile)

Max Activating Token Index: 824

Text #7

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5273. Min Act: -0.0000

Data Index: 1759900 (The Pile)

Max Activating Token Index: 710

Text #8

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6794. Min Act: -0.0000

Data Index: 1721637 (The Pile)

Max Activating Token Index: 219

Text #9

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1622043 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.6200. Min Act: -0.0000

Data Index: 766836 (The Pile)

Max Activating Token Index: 343

Text #11

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.5082. Min Act: -0.0000

Data Index: 81352 (The Pile)

Max Activating Token Index: 162

Text #12

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4661. Min Act: -0.0000

Data Index: 758982 (The Pile)

Max Activating Token Index: 86

Text #13

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4866. Min Act: -0.0000

Data Index: 1383613 (The Pile)

Max Activating Token Index: 319

Text #14

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4929. Min Act: -0.0000

Data Index: 1733716 (The Pile)

Max Activating Token Index: 681

Text #15

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.3653. Min Act: -0.0000

Data Index: 1718777 (The Pile)

Max Activating Token Index: 587

Text #16

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.3741. Min Act: -0.0000

Data Index: 861056 (The Pile)

Max Activating Token Index: 212

Text #17

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4022. Min Act: -0.0000

Data Index: 740663 (The Pile)

Max Activating Token Index: 377

Text #18

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4861. Min Act: -0.0000

Data Index: 202601 (The Pile)

Max Activating Token Index: 132

Text #19

Max Range: 1.7881. Min Range: -1.7881

Max Act: 1.4466. Min Act: -0.0000

Data Index: 1326690 (The Pile)

Max Activating Token Index: 517