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

Dataset: The Pile

Neuron 4288 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: 7.3233. Min Range: -7.3233

Max Act: 7.3233. Min Act: -0.0000

Data Index: 372717 (The Pile)

Max Activating Token Index: 39

Text #1

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.1238. Min Act: -0.0000

Data Index: 1921845 (The Pile)

Max Activating Token Index: 362

Text #2

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.8877. Min Act: -0.0000

Data Index: 246468 (The Pile)

Max Activating Token Index: 697

Text #3

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.1791. Min Act: -0.0000

Data Index: 1830579 (The Pile)

Max Activating Token Index: 45

Text #4

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.1505. Min Act: -0.0000

Data Index: 1809400 (The Pile)

Max Activating Token Index: 157

Text #5

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.1851. Min Act: -0.0000

Data Index: 15846 (The Pile)

Max Activating Token Index: 85

Text #6

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.9124. Min Act: -0.0000

Data Index: 308405 (The Pile)

Max Activating Token Index: 881

Text #7

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.0814. Min Act: -0.0000

Data Index: 1845769 (The Pile)

Max Activating Token Index: 71

Text #8

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.0357. Min Act: -0.0000

Data Index: 1393658 (The Pile)

Max Activating Token Index: 746

Text #9

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.0255. Min Act: -0.0000

Data Index: 742180 (The Pile)

Max Activating Token Index: 646

Text #10

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.7702. Min Act: -0.0000

Data Index: 1145492 (The Pile)

Max Activating Token Index: 472

Text #11

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.5138. Min Act: -0.0000

Data Index: 1077230 (The Pile)

Max Activating Token Index: 792

Text #12

Max Range: 7.3233. Min Range: -7.3233

Max Act: 7.0674. Min Act: -0.0000

Data Index: 131766 (The Pile)

Max Activating Token Index: 434

Text #13

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.8596. Min Act: -0.0000

Data Index: 865507 (The Pile)

Max Activating Token Index: 583

Text #14

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.8526. Min Act: -0.0000

Data Index: 469706 (The Pile)

Max Activating Token Index: 768

Text #15

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.7352. Min Act: -0.0000

Data Index: 483084 (The Pile)

Max Activating Token Index: 115

Text #16

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.7391. Min Act: -0.0000

Data Index: 1807014 (The Pile)

Max Activating Token Index: 224

Text #17

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.5492. Min Act: -0.0000

Data Index: 1045379 (The Pile)

Max Activating Token Index: 828

Text #18

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.9018. Min Act: -0.0000

Data Index: 893860 (The Pile)

Max Activating Token Index: 824

Text #19

Max Range: 7.3233. Min Range: -7.3233

Max Act: 6.4952. Min Act: -0.0000

Data Index: 346062 (The Pile)

Max Activating Token Index: 74