Model: SoLU Model: 8 Layers, 4096 Neurons per Layer

Dataset: The Pile

Neuron 3393 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-8l-pile')

Text #0

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.1756. Min Act: -0.0000

Data Index: 51140 (The Pile)

Max Activating Token Index: 941

Text #1

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9545. Min Act: -0.0000

Data Index: 988325 (The Pile)

Max Activating Token Index: 1000

Text #2

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0373. Min Act: -0.0000

Data Index: 601901 (The Pile)

Max Activating Token Index: 603

Text #3

Max Range: 1.1756. Min Range: -1.1756

Max Act: 1.0208. Min Act: -0.0000

Data Index: 1866966 (The Pile)

Max Activating Token Index: 885

Text #4

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9502. Min Act: -0.0000

Data Index: 1852213 (The Pile)

Max Activating Token Index: 355

Text #5

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9850. Min Act: -0.0000

Data Index: 733350 (The Pile)

Max Activating Token Index: 379

Text #6

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.9351. Min Act: -0.0000

Data Index: 408613 (The Pile)

Max Activating Token Index: 818

Text #7

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8430. Min Act: -0.0000

Data Index: 1801038 (The Pile)

Max Activating Token Index: 702

Text #8

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8434. Min Act: -0.0000

Data Index: 1429100 (The Pile)

Max Activating Token Index: 881

Text #9

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8771. Min Act: -0.0000

Data Index: 152396 (The Pile)

Max Activating Token Index: 300

Text #10

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8162. Min Act: -0.0000

Data Index: 391602 (The Pile)

Max Activating Token Index: 982

Text #11

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8656. Min Act: -0.0000

Data Index: 1828070 (The Pile)

Max Activating Token Index: 177

Text #12

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8612. Min Act: -0.0000

Data Index: 1046410 (The Pile)

Max Activating Token Index: 669

Text #13

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.7359. Min Act: -0.0000

Data Index: 1411915 (The Pile)

Max Activating Token Index: 549

Text #14

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8811. Min Act: -0.0000

Data Index: 1767621 (The Pile)

Max Activating Token Index: 477

Text #15

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.7593. Min Act: -0.0000

Data Index: 521985 (The Pile)

Max Activating Token Index: 476

Text #16

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8090. Min Act: -0.0000

Data Index: 579414 (The Pile)

Max Activating Token Index: 178

Text #17

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.8007. Min Act: -0.0000

Data Index: 512687 (The Pile)

Max Activating Token Index: 402

Text #18

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.7946. Min Act: -0.0000

Data Index: 355866 (The Pile)

Max Activating Token Index: 327

Text #19

Max Range: 1.1756. Min Range: -1.1756

Max Act: 0.7680. Min Act: -0.0000

Data Index: 453706 (The Pile)

Max Activating Token Index: 908