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

Dataset: The Pile

Neuron 4482 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: 3.0911. Min Range: -3.0911

Max Act: 3.0911. Min Act: -0.0000

Data Index: 950128 (The Pile)

Max Activating Token Index: 154

Text #1

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.7675. Min Act: -0.0000

Data Index: 990198 (The Pile)

Max Activating Token Index: 529

Text #2

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.7123. Min Act: -0.0000

Data Index: 429890 (The Pile)

Max Activating Token Index: 385

Text #3

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.3332. Min Act: -0.0000

Data Index: 1001303 (The Pile)

Max Activating Token Index: 617

Text #4

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.5040. Min Act: -0.0000

Data Index: 176046 (The Pile)

Max Activating Token Index: 554

Text #5

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.2519. Min Act: -0.0000

Data Index: 1288627 (The Pile)

Max Activating Token Index: 537

Text #6

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.9872. Min Act: -0.0000

Data Index: 1259909 (The Pile)

Max Activating Token Index: 1015

Text #7

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.2131. Min Act: -0.0000

Data Index: 1786463 (The Pile)

Max Activating Token Index: 339

Text #8

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.1828. Min Act: -0.0000

Data Index: 1911693 (The Pile)

Max Activating Token Index: 856

Text #9

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.8426. Min Act: -0.0000

Data Index: 1653406 (The Pile)

Max Activating Token Index: 174

Text #10

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.8592. Min Act: -0.0000

Data Index: 1164630 (The Pile)

Max Activating Token Index: 35

Text #11

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.8169. Min Act: -0.0000

Data Index: 1812062 (The Pile)

Max Activating Token Index: 353

Text #12

Max Range: 3.0911. Min Range: -3.0911

Max Act: 2.2634. Min Act: -0.0000

Data Index: 1340615 (The Pile)

Max Activating Token Index: 931

Text #13

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.8585. Min Act: -0.0000

Data Index: 1979452 (The Pile)

Max Activating Token Index: 914

Text #14

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.6292. Min Act: -0.0000

Data Index: 1615306 (The Pile)

Max Activating Token Index: 879

Text #15

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.6880. Min Act: -0.0000

Data Index: 542912 (The Pile)

Max Activating Token Index: 571

Text #16

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.7780. Min Act: -0.0000

Data Index: 1599086 (The Pile)

Max Activating Token Index: 429

Text #17

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.7977. Min Act: -0.0000

Data Index: 1142839 (The Pile)

Max Activating Token Index: 891

Text #18

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.6654. Min Act: -0.0000

Data Index: 605923 (The Pile)

Max Activating Token Index: 881

Text #19

Max Range: 3.0911. Min Range: -3.0911

Max Act: 1.6784. Min Act: -0.0000

Data Index: 119574 (The Pile)

Max Activating Token Index: 711