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

Dataset: The Pile

Neuron 3097 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: 0.9787. Min Range: -0.9787

Max Act: 0.9413. Min Act: 0.0000

Data Index: 112578 (The Pile)

Max Activating Token Index: 568

Text #1

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.9787. Min Act: -0.0000

Data Index: 610851 (The Pile)

Max Activating Token Index: 1018

Text #2

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8739. Min Act: -0.0000

Data Index: 1077742 (The Pile)

Max Activating Token Index: 747

Text #3

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7986. Min Act: -0.0000

Data Index: 741038 (The Pile)

Max Activating Token Index: 673

Text #4

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8060. Min Act: -0.0000

Data Index: 1833540 (The Pile)

Max Activating Token Index: 980

Text #5

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.8480. Min Act: -0.0000

Data Index: 1111271 (The Pile)

Max Activating Token Index: 847

Text #6

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7839. Min Act: -0.0000

Data Index: 1844117 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7893. Min Act: -0.0000

Data Index: 1231208 (The Pile)

Max Activating Token Index: 261

Text #8

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7811. Min Act: -0.0000

Data Index: 1201273 (The Pile)

Max Activating Token Index: 722

Text #9

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.7720. Min Act: -0.0000

Data Index: 68238 (The Pile)

Max Activating Token Index: 805

Text #10

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6760. Min Act: -0.0000

Data Index: 642798 (The Pile)

Max Activating Token Index: 505

Text #11

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6676. Min Act: -0.0000

Data Index: 1282099 (The Pile)

Max Activating Token Index: 273

Text #12

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6512. Min Act: -0.0000

Data Index: 480998 (The Pile)

Max Activating Token Index: 391

Text #13

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6863. Min Act: -0.0000

Data Index: 1832900 (The Pile)

Max Activating Token Index: 656

Text #14

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.5972. Min Act: -0.0000

Data Index: 345809 (The Pile)

Max Activating Token Index: 292

Text #15

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6195. Min Act: -0.0000

Data Index: 868736 (The Pile)

Max Activating Token Index: 254

Text #16

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1791924 (The Pile)

Max Activating Token Index: 681

Text #17

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6456. Min Act: -0.0000

Data Index: 763089 (The Pile)

Max Activating Token Index: 811

Text #18

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6314. Min Act: -0.0000

Data Index: 19851 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 0.9787. Min Range: -0.9787

Max Act: 0.6260. Min Act: 0.0000

Data Index: 509030 (The Pile)

Max Activating Token Index: 991