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

Dataset: The Pile

Neuron 1454 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2344. Min Act: -0.0000

Data Index: 1181263 (The Pile)

Max Activating Token Index: 855

Text #1

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2403. Min Act: -0.0000

Data Index: 975782 (The Pile)

Max Activating Token Index: 371

Text #2

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2336. Min Act: -0.0000

Data Index: 47739 (The Pile)

Max Activating Token Index: 567

Text #3

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2083. Min Act: -0.0000

Data Index: 1394838 (The Pile)

Max Activating Token Index: 804

Text #4

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2305. Min Act: -0.0000

Data Index: 1506682 (The Pile)

Max Activating Token Index: 642

Text #5

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2178. Min Act: -0.0000

Data Index: 1762919 (The Pile)

Max Activating Token Index: 575

Text #6

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2085. Min Act: -0.0000

Data Index: 245537 (The Pile)

Max Activating Token Index: 431

Text #7

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1930. Min Act: -0.0000

Data Index: 89616 (The Pile)

Max Activating Token Index: 753

Text #8

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1843. Min Act: -0.0000

Data Index: 1989649 (The Pile)

Max Activating Token Index: 630

Text #9

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1853. Min Act: -0.0000

Data Index: 1613356 (The Pile)

Max Activating Token Index: 856

Text #10

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1630. Min Act: -0.0000

Data Index: 1075549 (The Pile)

Max Activating Token Index: 874

Text #11

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2133. Min Act: -0.0000

Data Index: 172334 (The Pile)

Max Activating Token Index: 479

Text #12

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1907. Min Act: -0.0000

Data Index: 765952 (The Pile)

Max Activating Token Index: 945

Text #13

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.2100. Min Act: -0.0000

Data Index: 87053 (The Pile)

Max Activating Token Index: 646

Text #14

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1905. Min Act: -0.0000

Data Index: 142300 (The Pile)

Max Activating Token Index: 822

Text #15

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1628. Min Act: -0.0000

Data Index: 326408 (The Pile)

Max Activating Token Index: 705

Text #16

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1786. Min Act: -0.0000

Data Index: 360609 (The Pile)

Max Activating Token Index: 643

Text #17

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1890. Min Act: -0.0000

Data Index: 747248 (The Pile)

Max Activating Token Index: 236

Text #18

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1696. Min Act: -0.0000

Data Index: 1373867 (The Pile)

Max Activating Token Index: 506

Text #19

Max Range: 0.2403. Min Range: -0.2403

Max Act: 0.1751. Min Act: -0.0000

Data Index: 827585 (The Pile)

Max Activating Token Index: 393