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

Dataset: The Pile

Neuron 553 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: 0.8788. Min Range: -0.8788

Max Act: 0.8578. Min Act: -0.0000

Data Index: 1299246 (The Pile)

Max Activating Token Index: 602

Text #1

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8788. Min Act: -0.0000

Data Index: 142038 (The Pile)

Max Activating Token Index: 311

Text #2

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7983. Min Act: -0.0000

Data Index: 405184 (The Pile)

Max Activating Token Index: 929

Text #3

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8401. Min Act: -0.0000

Data Index: 1389574 (The Pile)

Max Activating Token Index: 135

Text #4

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8476. Min Act: -0.0000

Data Index: 1051128 (The Pile)

Max Activating Token Index: 541

Text #5

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7712. Min Act: -0.0000

Data Index: 504039 (The Pile)

Max Activating Token Index: 853

Text #6

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8681. Min Act: 0.0000

Data Index: 867844 (The Pile)

Max Activating Token Index: 272

Text #7

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7514. Min Act: -0.0000

Data Index: 508434 (The Pile)

Max Activating Token Index: 588

Text #8

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7130. Min Act: -0.0000

Data Index: 1972387 (The Pile)

Max Activating Token Index: 255

Text #9

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8640. Min Act: -0.0000

Data Index: 1581069 (The Pile)

Max Activating Token Index: 916

Text #10

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7661. Min Act: -0.0000

Data Index: 398606 (The Pile)

Max Activating Token Index: 506

Text #11

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8006. Min Act: -0.0000

Data Index: 1257622 (The Pile)

Max Activating Token Index: 1014

Text #12

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7832. Min Act: -0.0000

Data Index: 123667 (The Pile)

Max Activating Token Index: 986

Text #13

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7277. Min Act: -0.0000

Data Index: 384564 (The Pile)

Max Activating Token Index: 375

Text #14

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7005. Min Act: 0.0000

Data Index: 1482599 (The Pile)

Max Activating Token Index: 54

Text #15

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.8338. Min Act: 0.0000

Data Index: 131076 (The Pile)

Max Activating Token Index: 89

Text #16

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6360. Min Act: -0.0000

Data Index: 386155 (The Pile)

Max Activating Token Index: 930

Text #17

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6276. Min Act: -0.0000

Data Index: 1662862 (The Pile)

Max Activating Token Index: 969

Text #18

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.7290. Min Act: -0.0000

Data Index: 1798841 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 0.8788. Min Range: -0.8788

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1733676 (The Pile)

Max Activating Token Index: 683