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

Dataset: The Pile

Neuron 3998 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7562. Min Act: -0.0000

Data Index: 399173 (The Pile)

Max Activating Token Index: 848

Text #1

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7783. Min Act: -0.0000

Data Index: 848499 (The Pile)

Max Activating Token Index: 494

Text #2

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.8797. Min Act: -0.0000

Data Index: 751511 (The Pile)

Max Activating Token Index: 856

Text #3

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7662. Min Act: -0.0000

Data Index: 745000 (The Pile)

Max Activating Token Index: 854

Text #4

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.7720. Min Act: -0.0000

Data Index: 322806 (The Pile)

Max Activating Token Index: 27

Text #5

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6533. Min Act: -0.0000

Data Index: 484792 (The Pile)

Max Activating Token Index: 882

Text #6

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1978859 (The Pile)

Max Activating Token Index: 280

Text #7

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6355. Min Act: -0.0000

Data Index: 1757962 (The Pile)

Max Activating Token Index: 883

Text #8

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6357. Min Act: -0.0000

Data Index: 1847826 (The Pile)

Max Activating Token Index: 271

Text #9

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5465. Min Act: -0.0000

Data Index: 1157955 (The Pile)

Max Activating Token Index: 41

Text #10

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6494. Min Act: -0.0000

Data Index: 530218 (The Pile)

Max Activating Token Index: 535

Text #11

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6922. Min Act: -0.0000

Data Index: 447312 (The Pile)

Max Activating Token Index: 543

Text #12

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5902. Min Act: -0.0000

Data Index: 162776 (The Pile)

Max Activating Token Index: 432

Text #13

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6889. Min Act: -0.0000

Data Index: 1116957 (The Pile)

Max Activating Token Index: 790

Text #14

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6841. Min Act: -0.0000

Data Index: 1738381 (The Pile)

Max Activating Token Index: 65

Text #15

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6268. Min Act: -0.0000

Data Index: 1771415 (The Pile)

Max Activating Token Index: 28

Text #16

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.4298. Min Act: -0.0000

Data Index: 1401592 (The Pile)

Max Activating Token Index: 770

Text #17

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.5520. Min Act: -0.0000

Data Index: 85489 (The Pile)

Max Activating Token Index: 260

Text #18

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.6009. Min Act: -0.0000

Data Index: 1065583 (The Pile)

Max Activating Token Index: 562

Text #19

Max Range: 0.8797. Min Range: -0.8797

Max Act: 0.4972. Min Act: -0.0000

Data Index: 1303134 (The Pile)

Max Activating Token Index: 831