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

Dataset: The Pile

Neuron 2731 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.8451. Min Act: -0.0000

Data Index: 348726 (The Pile)

Max Activating Token Index: 917

Text #1

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.6812. Min Act: -0.0000

Data Index: 1676052 (The Pile)

Max Activating Token Index: 294

Text #2

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.4121. Min Act: -0.0000

Data Index: 74610 (The Pile)

Max Activating Token Index: 880

Text #3

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.5575. Min Act: -0.0000

Data Index: 818251 (The Pile)

Max Activating Token Index: 993

Text #4

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.5788. Min Act: -0.0000

Data Index: 1066518 (The Pile)

Max Activating Token Index: 396

Text #5

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.3698. Min Act: -0.0000

Data Index: 1004280 (The Pile)

Max Activating Token Index: 851

Text #6

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.5388. Min Act: -0.0000

Data Index: 1348123 (The Pile)

Max Activating Token Index: 945

Text #7

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.1866. Min Act: -0.0000

Data Index: 213503 (The Pile)

Max Activating Token Index: 983

Text #8

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.7624. Min Act: -0.0000

Data Index: 1567729 (The Pile)

Max Activating Token Index: 894

Text #9

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.4223. Min Act: -0.0000

Data Index: 1806945 (The Pile)

Max Activating Token Index: 594

Text #10

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.3910. Min Act: -0.0000

Data Index: 371325 (The Pile)

Max Activating Token Index: 825

Text #11

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.5901. Min Act: -0.0000

Data Index: 424583 (The Pile)

Max Activating Token Index: 968

Text #12

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.3110. Min Act: -0.0000

Data Index: 1114886 (The Pile)

Max Activating Token Index: 5

Text #13

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.3835. Min Act: -0.0000

Data Index: 114955 (The Pile)

Max Activating Token Index: 48

Text #14

Max Range: 3.8451. Min Range: -3.8451

Max Act: 2.9247. Min Act: -0.0000

Data Index: 146098 (The Pile)

Max Activating Token Index: 185

Text #15

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.1575. Min Act: -0.0000

Data Index: 542601 (The Pile)

Max Activating Token Index: 31

Text #16

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.1753. Min Act: -0.0000

Data Index: 699339 (The Pile)

Max Activating Token Index: 459

Text #17

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.1035. Min Act: -0.0000

Data Index: 1858606 (The Pile)

Max Activating Token Index: 268

Text #18

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.1421. Min Act: -0.0000

Data Index: 362099 (The Pile)

Max Activating Token Index: 234

Text #19

Max Range: 3.8451. Min Range: -3.8451

Max Act: 3.0922. Min Act: -0.0000

Data Index: 853 (The Pile)

Max Activating Token Index: 137