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

Dataset: The Pile

Neuron 3339 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: 0.6011. Min Range: -0.6011

Max Act: 0.6011. Min Act: -0.0000

Data Index: 977589 (The Pile)

Max Activating Token Index: 151

Text #1

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.1540. Min Act: -0.0000

Data Index: 1181893 (The Pile)

Max Activating Token Index: 978

Text #2

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.1392. Min Act: -0.0000

Data Index: 1308135 (The Pile)

Max Activating Token Index: 699

Text #3

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.1107. Min Act: -0.0000

Data Index: 1731791 (The Pile)

Max Activating Token Index: 370

Text #4

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.1024. Min Act: -0.0000

Data Index: 693348 (The Pile)

Max Activating Token Index: 827

Text #5

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0997. Min Act: -0.0000

Data Index: 914227 (The Pile)

Max Activating Token Index: 507

Text #6

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0956. Min Act: -0.0000

Data Index: 1917762 (The Pile)

Max Activating Token Index: 638

Text #7

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0971. Min Act: -0.0000

Data Index: 1258923 (The Pile)

Max Activating Token Index: 667

Text #8

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0903. Min Act: -0.0000

Data Index: 1335839 (The Pile)

Max Activating Token Index: 867

Text #9

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.1003. Min Act: -0.0000

Data Index: 1588695 (The Pile)

Max Activating Token Index: 498

Text #10

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0879. Min Act: -0.0000

Data Index: 245936 (The Pile)

Max Activating Token Index: 884

Text #11

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0908. Min Act: -0.0000

Data Index: 1707409 (The Pile)

Max Activating Token Index: 501

Text #12

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0939. Min Act: -0.0000

Data Index: 1318722 (The Pile)

Max Activating Token Index: 607

Text #13

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0936. Min Act: -0.0000

Data Index: 1569601 (The Pile)

Max Activating Token Index: 160

Text #14

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0899. Min Act: -0.0000

Data Index: 1801301 (The Pile)

Max Activating Token Index: 481

Text #15

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0906. Min Act: -0.0000

Data Index: 835787 (The Pile)

Max Activating Token Index: 751

Text #16

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0872. Min Act: -0.0000

Data Index: 1451038 (The Pile)

Max Activating Token Index: 611

Text #17

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0915. Min Act: -0.0000

Data Index: 1949557 (The Pile)

Max Activating Token Index: 389

Text #18

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0844. Min Act: -0.0000

Data Index: 214202 (The Pile)

Max Activating Token Index: 246

Text #19

Max Range: 0.6011. Min Range: -0.6011

Max Act: 0.0822. Min Act: -0.0000

Data Index: 748655 (The Pile)

Max Activating Token Index: 562