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

Dataset: The Pile

Neuron 2859 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1970. Min Act: -0.0000

Data Index: 587776 (The Pile)

Max Activating Token Index: 475

Text #1

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1812. Min Act: -0.0000

Data Index: 975966 (The Pile)

Max Activating Token Index: 502

Text #2

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1485. Min Act: -0.0000

Data Index: 1855758 (The Pile)

Max Activating Token Index: 998

Text #3

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.2385. Min Act: -0.0000

Data Index: 1033613 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9517. Min Act: -0.0000

Data Index: 1276602 (The Pile)

Max Activating Token Index: 666

Text #5

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.1235. Min Act: -0.0001

Data Index: 270825 (The Pile)

Max Activating Token Index: 592

Text #6

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0067. Min Act: -0.0001

Data Index: 1675695 (The Pile)

Max Activating Token Index: 567

Text #7

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0861. Min Act: -0.0000

Data Index: 1636182 (The Pile)

Max Activating Token Index: 68

Text #8

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0201. Min Act: -0.0000

Data Index: 1805864 (The Pile)

Max Activating Token Index: 367

Text #9

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0117. Min Act: -0.0000

Data Index: 860395 (The Pile)

Max Activating Token Index: 500

Text #10

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0666. Min Act: -0.0000

Data Index: 1756659 (The Pile)

Max Activating Token Index: 314

Text #11

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0371. Min Act: -0.0000

Data Index: 208197 (The Pile)

Max Activating Token Index: 13

Text #12

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9741. Min Act: -0.0000

Data Index: 32376 (The Pile)

Max Activating Token Index: 980

Text #13

Max Range: 1.2385. Min Range: -1.2385

Max Act: 1.0482. Min Act: -0.0000

Data Index: 1828433 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9561. Min Act: -0.0000

Data Index: 1151604 (The Pile)

Max Activating Token Index: 140

Text #15

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9886. Min Act: -0.0000

Data Index: 129306 (The Pile)

Max Activating Token Index: 693

Text #16

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9470. Min Act: -0.0000

Data Index: 1745972 (The Pile)

Max Activating Token Index: 152

Text #17

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9594. Min Act: -0.0000

Data Index: 757073 (The Pile)

Max Activating Token Index: 378

Text #18

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9801. Min Act: -0.0000

Data Index: 1824290 (The Pile)

Max Activating Token Index: 363

Text #19

Max Range: 1.2385. Min Range: -1.2385

Max Act: 0.9548. Min Act: -0.0000

Data Index: 1702079 (The Pile)

Max Activating Token Index: 861