Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 140 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.9914. Min Act: -0.0000

Data Index: 1770475 (The Pile)

Max Activating Token Index: 34

Text #1

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.9068. Min Act: -0.0000

Data Index: 456669 (The Pile)

Max Activating Token Index: 758

Text #2

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.8067. Min Act: -0.0000

Data Index: 480032 (The Pile)

Max Activating Token Index: 995

Text #3

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.7361. Min Act: -0.0000

Data Index: 372249 (The Pile)

Max Activating Token Index: 980

Text #4

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6305. Min Act: -0.0000

Data Index: 789810 (The Pile)

Max Activating Token Index: 622

Text #5

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6473. Min Act: -0.0000

Data Index: 1376926 (The Pile)

Max Activating Token Index: 341

Text #6

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5926. Min Act: -0.0000

Data Index: 349902 (The Pile)

Max Activating Token Index: 965

Text #7

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5867. Min Act: -0.0000

Data Index: 356099 (The Pile)

Max Activating Token Index: 500

Text #8

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5612. Min Act: -0.0000

Data Index: 982960 (The Pile)

Max Activating Token Index: 54

Text #9

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5561. Min Act: -0.0000

Data Index: 1854521 (The Pile)

Max Activating Token Index: 939

Text #10

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5720. Min Act: -0.0000

Data Index: 328166 (The Pile)

Max Activating Token Index: 114

Text #11

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5708. Min Act: -0.0000

Data Index: 1356958 (The Pile)

Max Activating Token Index: 326

Text #12

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.6126. Min Act: -0.0000

Data Index: 142489 (The Pile)

Max Activating Token Index: 999

Text #13

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5516. Min Act: -0.0000

Data Index: 916920 (The Pile)

Max Activating Token Index: 459

Text #14

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.4800. Min Act: -0.0000

Data Index: 1417425 (The Pile)

Max Activating Token Index: 873

Text #15

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5418. Min Act: -0.0000

Data Index: 902580 (The Pile)

Max Activating Token Index: 507

Text #16

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5170. Min Act: -0.0000

Data Index: 1969799 (The Pile)

Max Activating Token Index: 446

Text #17

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.4926. Min Act: -0.0000

Data Index: 1361115 (The Pile)

Max Activating Token Index: 561

Text #18

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5460. Min Act: -0.0000

Data Index: 1941648 (The Pile)

Max Activating Token Index: 86

Text #19

Max Range: 0.9914. Min Range: -0.9914

Max Act: 0.5381. Min Act: -0.0000

Data Index: 1781991 (The Pile)

Max Activating Token Index: 438