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

Dataset: The Pile

Neuron 1668 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: 0.8331. Min Range: -0.8331

Max Act: 0.8331. Min Act: -0.0000

Data Index: 822405 (The Pile)

Max Activating Token Index: 573

Text #1

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.6552. Min Act: -0.0000

Data Index: 599221 (The Pile)

Max Activating Token Index: 325

Text #2

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.6779. Min Act: -0.0000

Data Index: 102387 (The Pile)

Max Activating Token Index: 981

Text #3

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5886. Min Act: -0.0000

Data Index: 1780756 (The Pile)

Max Activating Token Index: 436

Text #4

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5979. Min Act: -0.0000

Data Index: 219392 (The Pile)

Max Activating Token Index: 813

Text #5

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.6324. Min Act: -0.0000

Data Index: 655812 (The Pile)

Max Activating Token Index: 729

Text #6

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5865. Min Act: -0.0000

Data Index: 471913 (The Pile)

Max Activating Token Index: 396

Text #7

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5803. Min Act: -0.0000

Data Index: 977386 (The Pile)

Max Activating Token Index: 589

Text #8

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5511. Min Act: -0.0000

Data Index: 964090 (The Pile)

Max Activating Token Index: 352

Text #9

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5996. Min Act: -0.0000

Data Index: 1153729 (The Pile)

Max Activating Token Index: 437

Text #10

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5112. Min Act: -0.0000

Data Index: 739870 (The Pile)

Max Activating Token Index: 92

Text #11

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5569. Min Act: -0.0000

Data Index: 1817747 (The Pile)

Max Activating Token Index: 362

Text #12

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5308. Min Act: -0.0000

Data Index: 1162243 (The Pile)

Max Activating Token Index: 123

Text #13

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5758. Min Act: -0.0000

Data Index: 89911 (The Pile)

Max Activating Token Index: 69

Text #14

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1527575 (The Pile)

Max Activating Token Index: 643

Text #15

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.4602. Min Act: -0.0000

Data Index: 534798 (The Pile)

Max Activating Token Index: 784

Text #16

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5407. Min Act: -0.0000

Data Index: 1067236 (The Pile)

Max Activating Token Index: 249

Text #17

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5143. Min Act: -0.0000

Data Index: 1290456 (The Pile)

Max Activating Token Index: 979

Text #18

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5209. Min Act: -0.0000

Data Index: 1699415 (The Pile)

Max Activating Token Index: 16

Text #19

Max Range: 0.8331. Min Range: -0.8331

Max Act: 0.5317. Min Act: -0.0000

Data Index: 1837361 (The Pile)

Max Activating Token Index: 888