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

Dataset: The Pile

Neuron 1430 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: 0.7915. Min Range: -0.7915

Max Act: 0.7915. Min Act: -0.0000

Data Index: 1869485 (The Pile)

Max Activating Token Index: 914

Text #1

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.7411. Min Act: -0.0000

Data Index: 420875 (The Pile)

Max Activating Token Index: 1017

Text #2

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6631. Min Act: -0.0000

Data Index: 1263120 (The Pile)

Max Activating Token Index: 379

Text #3

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6950. Min Act: -0.0000

Data Index: 1744347 (The Pile)

Max Activating Token Index: 125

Text #4

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6303. Min Act: -0.0000

Data Index: 1061613 (The Pile)

Max Activating Token Index: 690

Text #5

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6953. Min Act: -0.0000

Data Index: 1227194 (The Pile)

Max Activating Token Index: 169

Text #6

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5846. Min Act: -0.0000

Data Index: 525839 (The Pile)

Max Activating Token Index: 997

Text #7

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5991. Min Act: -0.0000

Data Index: 1653645 (The Pile)

Max Activating Token Index: 477

Text #8

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5425. Min Act: -0.0000

Data Index: 1477307 (The Pile)

Max Activating Token Index: 818

Text #9

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5189. Min Act: -0.0000

Data Index: 1221143 (The Pile)

Max Activating Token Index: 246

Text #10

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5655. Min Act: -0.0000

Data Index: 798309 (The Pile)

Max Activating Token Index: 527

Text #11

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5996. Min Act: -0.0000

Data Index: 558133 (The Pile)

Max Activating Token Index: 40

Text #12

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5448. Min Act: -0.0000

Data Index: 169332 (The Pile)

Max Activating Token Index: 585

Text #13

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5801. Min Act: -0.0000

Data Index: 560490 (The Pile)

Max Activating Token Index: 490

Text #14

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5751. Min Act: -0.0000

Data Index: 1321756 (The Pile)

Max Activating Token Index: 790

Text #15

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.6104. Min Act: -0.0000

Data Index: 598645 (The Pile)

Max Activating Token Index: 428

Text #16

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.4784. Min Act: -0.0000

Data Index: 1922306 (The Pile)

Max Activating Token Index: 919

Text #17

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5351. Min Act: -0.0000

Data Index: 1137561 (The Pile)

Max Activating Token Index: 551

Text #18

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5514. Min Act: -0.0000

Data Index: 251888 (The Pile)

Max Activating Token Index: 717

Text #19

Max Range: 0.7915. Min Range: -0.7915

Max Act: 0.5449. Min Act: -0.0000

Data Index: 90372 (The Pile)

Max Activating Token Index: 688