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

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 4726 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.7695. Min Act: -0.0000

Data Index: 566101 (C4 (Web Text))

Max Activating Token Index: 869

Text #1

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6938. Min Act: -0.0000

Data Index: 1007958 (C4 (Web Text))

Max Activating Token Index: 362

Text #2

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6736. Min Act: -0.0000

Data Index: 1236448 (C4 (Web Text))

Max Activating Token Index: 69

Text #3

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6936. Min Act: -0.0000

Data Index: 457768 (C4 (Web Text))

Max Activating Token Index: 400

Text #4

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6849. Min Act: -0.0000

Data Index: 1117468 (C4 (Web Text))

Max Activating Token Index: 874

Text #5

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6608. Min Act: -0.0000

Data Index: 1077905 (C4 (Web Text))

Max Activating Token Index: 767

Text #6

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6928. Min Act: -0.0000

Data Index: 897594 (C4 (Web Text))

Max Activating Token Index: 835

Text #7

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6680. Min Act: -0.0000

Data Index: 360758 (C4 (Web Text))

Max Activating Token Index: 332

Text #8

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6194. Min Act: -0.0000

Data Index: 215949 (C4 (Web Text))

Max Activating Token Index: 375

Text #9

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6365. Min Act: -0.0000

Data Index: 646160 (C4 (Web Text))

Max Activating Token Index: 333

Text #10

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6230. Min Act: -0.0000

Data Index: 792407 (C4 (Web Text))

Max Activating Token Index: 486

Text #11

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5966. Min Act: -0.0000

Data Index: 807683 (C4 (Web Text))

Max Activating Token Index: 568

Text #12

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6121. Min Act: -0.0000

Data Index: 518118 (C4 (Web Text))

Max Activating Token Index: 496

Text #13

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5971. Min Act: 0.0000

Data Index: 1076644 (C4 (Web Text))

Max Activating Token Index: 593

Text #14

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6100. Min Act: -0.0000

Data Index: 307774 (C4 (Web Text))

Max Activating Token Index: 454

Text #15

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6127. Min Act: -0.0000

Data Index: 972381 (C4 (Web Text))

Max Activating Token Index: 902

Text #16

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.6007. Min Act: -0.0000

Data Index: 180274 (C4 (Web Text))

Max Activating Token Index: 49

Text #17

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5820. Min Act: -0.0000

Data Index: 314661 (C4 (Web Text))

Max Activating Token Index: 810

Text #18

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5645. Min Act: -0.0000

Data Index: 77936 (C4 (Web Text))

Max Activating Token Index: 838

Text #19

Max Range: 0.7695. Min Range: -0.7695

Max Act: 0.5796. Min Act: -0.0000

Data Index: 1283216 (C4 (Web Text))

Max Activating Token Index: 761