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

Dataset: The Pile

Neuron 4606 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: 1.1825. Min Range: -1.1825

Max Act: 1.1238. Min Act: -0.0000

Data Index: 502526 (The Pile)

Max Activating Token Index: 751

Text #1

Max Range: 1.1825. Min Range: -1.1825

Max Act: 1.1825. Min Act: -0.0000

Data Index: 337274 (The Pile)

Max Activating Token Index: 822

Text #2

Max Range: 1.1825. Min Range: -1.1825

Max Act: 1.0741. Min Act: -0.0000

Data Index: 1354213 (The Pile)

Max Activating Token Index: 848

Text #3

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.9261. Min Act: -0.0000

Data Index: 1148102 (The Pile)

Max Activating Token Index: 694

Text #4

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.9934. Min Act: -0.0000

Data Index: 554052 (The Pile)

Max Activating Token Index: 549

Text #5

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1348100 (The Pile)

Max Activating Token Index: 362

Text #6

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.8311. Min Act: -0.0000

Data Index: 634329 (The Pile)

Max Activating Token Index: 440

Text #7

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.8014. Min Act: -0.0000

Data Index: 665025 (The Pile)

Max Activating Token Index: 709

Text #8

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.7848. Min Act: -0.0000

Data Index: 1030220 (The Pile)

Max Activating Token Index: 135

Text #9

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.7765. Min Act: -0.0000

Data Index: 963405 (The Pile)

Max Activating Token Index: 382

Text #10

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.6441. Min Act: -0.0000

Data Index: 450208 (The Pile)

Max Activating Token Index: 569

Text #11

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.7436. Min Act: -0.0000

Data Index: 596312 (The Pile)

Max Activating Token Index: 108

Text #12

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.6869. Min Act: -0.0000

Data Index: 887271 (The Pile)

Max Activating Token Index: 904

Text #13

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.6648. Min Act: -0.0000

Data Index: 516118 (The Pile)

Max Activating Token Index: 902

Text #14

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.7114. Min Act: -0.0000

Data Index: 1643856 (The Pile)

Max Activating Token Index: 577

Text #15

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.7699. Min Act: -0.0000

Data Index: 810882 (The Pile)

Max Activating Token Index: 584

Text #16

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.6060. Min Act: -0.0000

Data Index: 1374837 (The Pile)

Max Activating Token Index: 736

Text #17

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.5727. Min Act: -0.0000

Data Index: 959491 (The Pile)

Max Activating Token Index: 661

Text #18

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.6196. Min Act: -0.0000

Data Index: 1633748 (The Pile)

Max Activating Token Index: 597

Text #19

Max Range: 1.1825. Min Range: -1.1825

Max Act: 0.5945. Min Act: -0.0000

Data Index: 1588637 (The Pile)

Max Activating Token Index: 996