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

Dataset: The Pile

Neuron 2665 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: 0.9840. Min Range: -0.9840

Max Act: 0.9840. Min Act: -0.0000

Data Index: 28796 (The Pile)

Max Activating Token Index: 887

Text #1

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7241. Min Act: -0.0000

Data Index: 1987643 (The Pile)

Max Activating Token Index: 312

Text #2

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6934. Min Act: -0.0000

Data Index: 1072102 (The Pile)

Max Activating Token Index: 165

Text #3

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.7335. Min Act: -0.0000

Data Index: 488746 (The Pile)

Max Activating Token Index: 82

Text #4

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6478. Min Act: -0.0000

Data Index: 1561431 (The Pile)

Max Activating Token Index: 504

Text #5

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6295. Min Act: -0.0000

Data Index: 1973608 (The Pile)

Max Activating Token Index: 107

Text #6

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6123. Min Act: -0.0000

Data Index: 37869 (The Pile)

Max Activating Token Index: 322

Text #7

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5251. Min Act: -0.0000

Data Index: 905465 (The Pile)

Max Activating Token Index: 817

Text #8

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5273. Min Act: -0.0000

Data Index: 879472 (The Pile)

Max Activating Token Index: 738

Text #9

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6440. Min Act: -0.0000

Data Index: 881439 (The Pile)

Max Activating Token Index: 388

Text #10

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6118. Min Act: -0.0000

Data Index: 133829 (The Pile)

Max Activating Token Index: 661

Text #11

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5895. Min Act: -0.0000

Data Index: 404334 (The Pile)

Max Activating Token Index: 371

Text #12

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6235. Min Act: 0.0000

Data Index: 1046960 (The Pile)

Max Activating Token Index: 361

Text #13

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5549. Min Act: -0.0000

Data Index: 1940740 (The Pile)

Max Activating Token Index: 510

Text #14

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.6138. Min Act: -0.0000

Data Index: 1659981 (The Pile)

Max Activating Token Index: 732

Text #15

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5858. Min Act: -0.0000

Data Index: 1514367 (The Pile)

Max Activating Token Index: 850

Text #16

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5568. Min Act: -0.0000

Data Index: 1802614 (The Pile)

Max Activating Token Index: 860

Text #17

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5442. Min Act: -0.0000

Data Index: 1129203 (The Pile)

Max Activating Token Index: 1008

Text #18

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5845. Min Act: -0.0000

Data Index: 797375 (The Pile)

Max Activating Token Index: 982

Text #19

Max Range: 0.9840. Min Range: -0.9840

Max Act: 0.5639. Min Act: -0.0000

Data Index: 483436 (The Pile)

Max Activating Token Index: 291