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

Dataset: The Pile

Neuron 4700 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8869. Min Act: -0.0000

Data Index: 620249 (The Pile)

Max Activating Token Index: 502

Text #1

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7352. Min Act: -0.0000

Data Index: 1909284 (The Pile)

Max Activating Token Index: 823

Text #2

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1970858 (The Pile)

Max Activating Token Index: 564

Text #3

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7252. Min Act: -0.0000

Data Index: 1900971 (The Pile)

Max Activating Token Index: 62

Text #4

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.7432. Min Act: -0.0000

Data Index: 1502652 (The Pile)

Max Activating Token Index: 689

Text #5

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6897. Min Act: -0.0000

Data Index: 123599 (The Pile)

Max Activating Token Index: 49

Text #6

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6711. Min Act: 0.0000

Data Index: 595073 (The Pile)

Max Activating Token Index: 641

Text #7

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6603. Min Act: -0.0000

Data Index: 145860 (The Pile)

Max Activating Token Index: 222

Text #8

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6148. Min Act: -0.0000

Data Index: 900220 (The Pile)

Max Activating Token Index: 392

Text #9

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6530. Min Act: -0.0000

Data Index: 216762 (The Pile)

Max Activating Token Index: 593

Text #10

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5691. Min Act: -0.0000

Data Index: 391324 (The Pile)

Max Activating Token Index: 756

Text #11

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5473. Min Act: -0.0000

Data Index: 1412269 (The Pile)

Max Activating Token Index: 883

Text #12

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.6238. Min Act: -0.0000

Data Index: 1472364 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5641. Min Act: 0.0000

Data Index: 1102030 (The Pile)

Max Activating Token Index: 975

Text #14

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5799. Min Act: -0.0000

Data Index: 841625 (The Pile)

Max Activating Token Index: 772

Text #15

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5573. Min Act: -0.0000

Data Index: 1240655 (The Pile)

Max Activating Token Index: 838

Text #16

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5377. Min Act: -0.0000

Data Index: 379460 (The Pile)

Max Activating Token Index: 968

Text #17

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5458. Min Act: 0.0000

Data Index: 1279698 (The Pile)

Max Activating Token Index: 773

Text #18

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5755. Min Act: 0.0000

Data Index: 834983 (The Pile)

Max Activating Token Index: 337

Text #19

Max Range: 0.8869. Min Range: -0.8869

Max Act: 0.5125. Min Act: -0.0000

Data Index: 599636 (The Pile)

Max Activating Token Index: 709