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

Dataset: The Pile

Neuron 51 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.8057. Min Act: -0.0000

Data Index: 1344079 (The Pile)

Max Activating Token Index: 465

Text #1

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.4429. Min Act: -0.0000

Data Index: 37641 (The Pile)

Max Activating Token Index: 464

Text #2

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.5129. Min Act: -0.0000

Data Index: 1188129 (The Pile)

Max Activating Token Index: 997

Text #3

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1154. Min Act: -0.0000

Data Index: 417977 (The Pile)

Max Activating Token Index: 919

Text #4

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.3265. Min Act: -0.0000

Data Index: 663991 (The Pile)

Max Activating Token Index: 860

Text #5

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.3114. Min Act: -0.0000

Data Index: 101517 (The Pile)

Max Activating Token Index: 57

Text #6

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.2610. Min Act: -0.0000

Data Index: 263063 (The Pile)

Max Activating Token Index: 402

Text #7

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1194. Min Act: -0.0000

Data Index: 303360 (The Pile)

Max Activating Token Index: 767

Text #8

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.0853. Min Act: -0.0000

Data Index: 1561799 (The Pile)

Max Activating Token Index: 667

Text #9

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9964. Min Act: -0.0000

Data Index: 121155 (The Pile)

Max Activating Token Index: 1006

Text #10

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.1446. Min Act: -0.0000

Data Index: 1963383 (The Pile)

Max Activating Token Index: 898

Text #11

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.0794. Min Act: -0.0000

Data Index: 683462 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.0642. Min Act: -0.0000

Data Index: 97845 (The Pile)

Max Activating Token Index: 886

Text #13

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.2485. Min Act: -0.0000

Data Index: 1405433 (The Pile)

Max Activating Token Index: 794

Text #14

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.0645. Min Act: -0.0000

Data Index: 648383 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9097. Min Act: -0.0000

Data Index: 1960372 (The Pile)

Max Activating Token Index: 829

Text #16

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.2073. Min Act: -0.0000

Data Index: 973202 (The Pile)

Max Activating Token Index: 785

Text #17

Max Range: 3.8057. Min Range: -3.8057

Max Act: 3.0476. Min Act: -0.0000

Data Index: 1039579 (The Pile)

Max Activating Token Index: 873

Text #18

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9909. Min Act: -0.0000

Data Index: 546967 (The Pile)

Max Activating Token Index: 971

Text #19

Max Range: 3.8057. Min Range: -3.8057

Max Act: 2.9825. Min Act: -0.0000

Data Index: 1126446 (The Pile)

Max Activating Token Index: 945