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

Dataset: The Pile

Neuron 2530 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8783. Min Act: 0.0000

Data Index: 852994 (The Pile)

Max Activating Token Index: 989

Text #1

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.9429. Min Act: -0.0000

Data Index: 743729 (The Pile)

Max Activating Token Index: 81

Text #2

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.8471. Min Act: 0.0000

Data Index: 457540 (The Pile)

Max Activating Token Index: 372

Text #3

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6199. Min Act: -0.0000

Data Index: 795714 (The Pile)

Max Activating Token Index: 855

Text #4

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7772. Min Act: -0.0000

Data Index: 1529810 (The Pile)

Max Activating Token Index: 618

Text #5

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7043. Min Act: -0.0000

Data Index: 311200 (The Pile)

Max Activating Token Index: 593

Text #6

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7110. Min Act: -0.0000

Data Index: 1150296 (The Pile)

Max Activating Token Index: 202

Text #7

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6794. Min Act: -0.0000

Data Index: 764468 (The Pile)

Max Activating Token Index: 527

Text #8

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.7231. Min Act: -0.0000

Data Index: 1348316 (The Pile)

Max Activating Token Index: 222

Text #9

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6273. Min Act: -0.0000

Data Index: 1565700 (The Pile)

Max Activating Token Index: 1008

Text #10

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6986. Min Act: -0.0000

Data Index: 1393081 (The Pile)

Max Activating Token Index: 429

Text #11

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6756. Min Act: -0.0000

Data Index: 1814717 (The Pile)

Max Activating Token Index: 466

Text #12

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6271. Min Act: -0.0000

Data Index: 994529 (The Pile)

Max Activating Token Index: 42

Text #13

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6562. Min Act: -0.0000

Data Index: 1854868 (The Pile)

Max Activating Token Index: 590

Text #14

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6527. Min Act: 0.0000

Data Index: 1125113 (The Pile)

Max Activating Token Index: 757

Text #15

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6869. Min Act: -0.0000

Data Index: 9650 (The Pile)

Max Activating Token Index: 352

Text #16

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6433. Min Act: 0.0000

Data Index: 1595876 (The Pile)

Max Activating Token Index: 946

Text #17

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6469. Min Act: 0.0000

Data Index: 1233829 (The Pile)

Max Activating Token Index: 759

Text #18

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.6131. Min Act: -0.0000

Data Index: 1901200 (The Pile)

Max Activating Token Index: 715

Text #19

Max Range: 0.9429. Min Range: -0.9429

Max Act: 0.5895. Min Act: -0.0000

Data Index: 620696 (The Pile)

Max Activating Token Index: 609