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

Dataset: The Pile

Neuron 4763 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: 1.8869. Min Range: -1.8869

Max Act: 1.8869. Min Act: -0.0000

Data Index: 1930293 (The Pile)

Max Activating Token Index: 60

Text #1

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7058. Min Act: -0.0000

Data Index: 473562 (The Pile)

Max Activating Token Index: 367

Text #2

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6045. Min Act: -0.0000

Data Index: 468973 (The Pile)

Max Activating Token Index: 486

Text #3

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7183. Min Act: -0.0000

Data Index: 209736 (The Pile)

Max Activating Token Index: 68

Text #4

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6120. Min Act: -0.0000

Data Index: 1382812 (The Pile)

Max Activating Token Index: 491

Text #5

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6619. Min Act: -0.0000

Data Index: 1537021 (The Pile)

Max Activating Token Index: 616

Text #6

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5421. Min Act: -0.0000

Data Index: 1875404 (The Pile)

Max Activating Token Index: 799

Text #7

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6392. Min Act: -0.0000

Data Index: 1228673 (The Pile)

Max Activating Token Index: 643

Text #8

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7196. Min Act: -0.0000

Data Index: 404599 (The Pile)

Max Activating Token Index: 642

Text #9

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.7188. Min Act: -0.0000

Data Index: 609372 (The Pile)

Max Activating Token Index: 674

Text #10

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5378. Min Act: -0.0000

Data Index: 1464430 (The Pile)

Max Activating Token Index: 730

Text #11

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6338. Min Act: -0.0000

Data Index: 1477791 (The Pile)

Max Activating Token Index: 642

Text #12

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5336. Min Act: -0.0000

Data Index: 161607 (The Pile)

Max Activating Token Index: 704

Text #13

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6244. Min Act: -0.0000

Data Index: 1476905 (The Pile)

Max Activating Token Index: 491

Text #14

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5283. Min Act: -0.0000

Data Index: 1400268 (The Pile)

Max Activating Token Index: 303

Text #15

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5236. Min Act: -0.0000

Data Index: 1013080 (The Pile)

Max Activating Token Index: 334

Text #16

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6128. Min Act: -0.0000

Data Index: 891509 (The Pile)

Max Activating Token Index: 512

Text #17

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6204. Min Act: -0.0000

Data Index: 1057026 (The Pile)

Max Activating Token Index: 599

Text #18

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.5193. Min Act: -0.0000

Data Index: 1555595 (The Pile)

Max Activating Token Index: 464

Text #19

Max Range: 1.8869. Min Range: -1.8869

Max Act: 1.6029. Min Act: -0.0000

Data Index: 1720603 (The Pile)

Max Activating Token Index: 341