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

Dataset: The Pile

Neuron 4518 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: 1.7076. Min Range: -1.7076

Max Act: 1.7076. Min Act: -0.0000

Data Index: 1324354 (The Pile)

Max Activating Token Index: 22

Text #1

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.5005. Min Act: -0.0000

Data Index: 1079779 (The Pile)

Max Activating Token Index: 205

Text #2

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.4473. Min Act: -0.0000

Data Index: 411734 (The Pile)

Max Activating Token Index: 335

Text #3

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.2848. Min Act: -0.0000

Data Index: 542768 (The Pile)

Max Activating Token Index: 945

Text #4

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.4929. Min Act: -0.0000

Data Index: 1258014 (The Pile)

Max Activating Token Index: 293

Text #5

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.3929. Min Act: -0.0000

Data Index: 931545 (The Pile)

Max Activating Token Index: 850

Text #6

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.3571. Min Act: -0.0000

Data Index: 1440359 (The Pile)

Max Activating Token Index: 759

Text #7

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.3429. Min Act: -0.0000

Data Index: 1350769 (The Pile)

Max Activating Token Index: 886

Text #8

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.3351. Min Act: -0.0000

Data Index: 760731 (The Pile)

Max Activating Token Index: 413

Text #9

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.5443. Min Act: -0.0000

Data Index: 1937223 (The Pile)

Max Activating Token Index: 844

Text #10

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.4211. Min Act: -0.0000

Data Index: 360880 (The Pile)

Max Activating Token Index: 99

Text #11

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.3096. Min Act: -0.0000

Data Index: 1602013 (The Pile)

Max Activating Token Index: 10

Text #12

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.2932. Min Act: -0.0000

Data Index: 1296456 (The Pile)

Max Activating Token Index: 438

Text #13

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.2612. Min Act: -0.0000

Data Index: 891460 (The Pile)

Max Activating Token Index: 882

Text #14

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.1046. Min Act: -0.0000

Data Index: 165934 (The Pile)

Max Activating Token Index: 164

Text #15

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.2447. Min Act: -0.0000

Data Index: 1689167 (The Pile)

Max Activating Token Index: 810

Text #16

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.1028. Min Act: -0.0000

Data Index: 1277465 (The Pile)

Max Activating Token Index: 284

Text #17

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.2949. Min Act: -0.0000

Data Index: 1368729 (The Pile)

Max Activating Token Index: 8

Text #18

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.1902. Min Act: -0.0000

Data Index: 1701415 (The Pile)

Max Activating Token Index: 782

Text #19

Max Range: 1.7076. Min Range: -1.7076

Max Act: 1.2163. Min Act: -0.0000

Data Index: 571772 (The Pile)

Max Activating Token Index: 53