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

Dataset: The Pile

Neuron 1400 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.3523. Min Act: -0.0000

Data Index: 331125 (The Pile)

Max Activating Token Index: 477

Text #1

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.1011. Min Act: -0.0000

Data Index: 1863770 (The Pile)

Max Activating Token Index: 942

Text #2

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0412. Min Act: -0.0000

Data Index: 1080700 (The Pile)

Max Activating Token Index: 900

Text #3

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0149. Min Act: -0.0000

Data Index: 1651250 (The Pile)

Max Activating Token Index: 563

Text #4

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0858. Min Act: -0.0000

Data Index: 72337 (The Pile)

Max Activating Token Index: 872

Text #5

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9859. Min Act: -0.0000

Data Index: 1322543 (The Pile)

Max Activating Token Index: 883

Text #6

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9647. Min Act: -0.0000

Data Index: 551507 (The Pile)

Max Activating Token Index: 252

Text #7

Max Range: 1.3523. Min Range: -1.3523

Max Act: 1.0119. Min Act: -0.0000

Data Index: 716571 (The Pile)

Max Activating Token Index: 499

Text #8

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9448. Min Act: -0.0000

Data Index: 1142819 (The Pile)

Max Activating Token Index: 610

Text #9

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9366. Min Act: -0.0000

Data Index: 701170 (The Pile)

Max Activating Token Index: 583

Text #10

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9360. Min Act: -0.0000

Data Index: 94008 (The Pile)

Max Activating Token Index: 932

Text #11

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9299. Min Act: -0.0000

Data Index: 1315859 (The Pile)

Max Activating Token Index: 513

Text #12

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.9833. Min Act: -0.0000

Data Index: 1510305 (The Pile)

Max Activating Token Index: 738

Text #13

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.8903. Min Act: -0.0000

Data Index: 322319 (The Pile)

Max Activating Token Index: 946

Text #14

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.8705. Min Act: -0.0000

Data Index: 113528 (The Pile)

Max Activating Token Index: 63

Text #15

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.7935. Min Act: -0.0000

Data Index: 917582 (The Pile)

Max Activating Token Index: 603

Text #16

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.8876. Min Act: -0.0000

Data Index: 661001 (The Pile)

Max Activating Token Index: 777

Text #17

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.7836. Min Act: -0.0000

Data Index: 1917931 (The Pile)

Max Activating Token Index: 180

Text #18

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.8196. Min Act: -0.0000

Data Index: 1319610 (The Pile)

Max Activating Token Index: 303

Text #19

Max Range: 1.3523. Min Range: -1.3523

Max Act: 0.8040. Min Act: -0.0000

Data Index: 1313533 (The Pile)

Max Activating Token Index: 233