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

Dataset: The Pile

Neuron 111 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: 0.9807. Min Range: -0.9807

Max Act: 0.9237. Min Act: -0.0000

Data Index: 8185 (The Pile)

Max Activating Token Index: 506

Text #1

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8790. Min Act: -0.0000

Data Index: 487795 (The Pile)

Max Activating Token Index: 637

Text #2

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9807. Min Act: -0.0000

Data Index: 326664 (The Pile)

Max Activating Token Index: 175

Text #3

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8997. Min Act: -0.0000

Data Index: 1842860 (The Pile)

Max Activating Token Index: 10

Text #4

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9107. Min Act: -0.0000

Data Index: 448199 (The Pile)

Max Activating Token Index: 769

Text #5

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8211. Min Act: -0.0000

Data Index: 245939 (The Pile)

Max Activating Token Index: 76

Text #6

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7722. Min Act: -0.0000

Data Index: 680033 (The Pile)

Max Activating Token Index: 704

Text #7

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7847. Min Act: -0.0000

Data Index: 1123434 (The Pile)

Max Activating Token Index: 884

Text #8

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7784. Min Act: -0.0000

Data Index: 13647 (The Pile)

Max Activating Token Index: 735

Text #9

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.9051. Min Act: -0.0000

Data Index: 219952 (The Pile)

Max Activating Token Index: 908

Text #10

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.8220. Min Act: -0.0000

Data Index: 162148 (The Pile)

Max Activating Token Index: 485

Text #11

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7865. Min Act: -0.0000

Data Index: 751814 (The Pile)

Max Activating Token Index: 301

Text #12

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7047. Min Act: -0.0000

Data Index: 1587843 (The Pile)

Max Activating Token Index: 820

Text #13

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7272. Min Act: -0.0000

Data Index: 400751 (The Pile)

Max Activating Token Index: 94

Text #14

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7275. Min Act: -0.0000

Data Index: 453339 (The Pile)

Max Activating Token Index: 616

Text #15

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7713. Min Act: -0.0000

Data Index: 1341117 (The Pile)

Max Activating Token Index: 463

Text #16

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7664. Min Act: -0.0000

Data Index: 860069 (The Pile)

Max Activating Token Index: 582

Text #17

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7574. Min Act: -0.0000

Data Index: 482517 (The Pile)

Max Activating Token Index: 653

Text #18

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7502. Min Act: -0.0000

Data Index: 584959 (The Pile)

Max Activating Token Index: 1013

Text #19

Max Range: 0.9807. Min Range: -0.9807

Max Act: 0.7281. Min Act: -0.0000

Data Index: 1264122 (The Pile)

Max Activating Token Index: 702