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

Dataset: The Pile

Neuron 3990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6615. Min Act: -0.0000

Data Index: 1836013 (The Pile)

Max Activating Token Index: 897

Text #1

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6543. Min Act: -0.0000

Data Index: 1536399 (The Pile)

Max Activating Token Index: 424

Text #2

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6629. Min Act: -0.0000

Data Index: 171359 (The Pile)

Max Activating Token Index: 268

Text #3

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6023. Min Act: -0.0000

Data Index: 214913 (The Pile)

Max Activating Token Index: 642

Text #4

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6250. Min Act: -0.0000

Data Index: 1869067 (The Pile)

Max Activating Token Index: 38

Text #5

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5692. Min Act: -0.0000

Data Index: 1882918 (The Pile)

Max Activating Token Index: 799

Text #6

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6429. Min Act: -0.0000

Data Index: 1626170 (The Pile)

Max Activating Token Index: 474

Text #7

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5037. Min Act: -0.0000

Data Index: 1094322 (The Pile)

Max Activating Token Index: 633

Text #8

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6182. Min Act: -0.0000

Data Index: 1607558 (The Pile)

Max Activating Token Index: 711

Text #9

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5570. Min Act: -0.0000

Data Index: 1680034 (The Pile)

Max Activating Token Index: 1013

Text #10

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5420. Min Act: -0.0000

Data Index: 1765103 (The Pile)

Max Activating Token Index: 871

Text #11

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5505. Min Act: -0.0000

Data Index: 390998 (The Pile)

Max Activating Token Index: 561

Text #12

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5159. Min Act: -0.0000

Data Index: 512765 (The Pile)

Max Activating Token Index: 392

Text #13

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5496. Min Act: -0.0000

Data Index: 270064 (The Pile)

Max Activating Token Index: 166

Text #14

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5273. Min Act: -0.0000

Data Index: 637661 (The Pile)

Max Activating Token Index: 25

Text #15

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5125. Min Act: -0.0000

Data Index: 549691 (The Pile)

Max Activating Token Index: 552

Text #16

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5739. Min Act: -0.0000

Data Index: 1359986 (The Pile)

Max Activating Token Index: 261

Text #17

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5171. Min Act: -0.0000

Data Index: 524931 (The Pile)

Max Activating Token Index: 923

Text #18

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.6021. Min Act: -0.0000

Data Index: 729235 (The Pile)

Max Activating Token Index: 380

Text #19

Max Range: 0.6629. Min Range: -0.6629

Max Act: 0.5112. Min Act: -0.0000

Data Index: 32372 (The Pile)

Max Activating Token Index: 732