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

Dataset: The Pile

Neuron 758 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: 1.2781. Min Range: -1.2781

Max Act: 1.2781. Min Act: -0.0000

Data Index: 1245963 (The Pile)

Max Activating Token Index: 335

Text #1

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9505. Min Act: 0.0000

Data Index: 726645 (The Pile)

Max Activating Token Index: 47

Text #2

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.9437. Min Act: -0.0000

Data Index: 1570589 (The Pile)

Max Activating Token Index: 987

Text #3

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8517. Min Act: -0.0000

Data Index: 1673415 (The Pile)

Max Activating Token Index: 696

Text #4

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8340. Min Act: -0.0000

Data Index: 24745 (The Pile)

Max Activating Token Index: 570

Text #5

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8319. Min Act: 0.0000

Data Index: 1266865 (The Pile)

Max Activating Token Index: 226

Text #6

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8101. Min Act: -0.0000

Data Index: 1952528 (The Pile)

Max Activating Token Index: 664

Text #7

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8152. Min Act: -0.0000

Data Index: 121526 (The Pile)

Max Activating Token Index: 663

Text #8

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7985. Min Act: -0.0000

Data Index: 1927006 (The Pile)

Max Activating Token Index: 770

Text #9

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7744. Min Act: -0.0000

Data Index: 1270453 (The Pile)

Max Activating Token Index: 376

Text #10

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7727. Min Act: -0.0000

Data Index: 1322688 (The Pile)

Max Activating Token Index: 247

Text #11

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7481. Min Act: -0.0000

Data Index: 1909423 (The Pile)

Max Activating Token Index: 922

Text #12

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7984. Min Act: -0.0000

Data Index: 1755263 (The Pile)

Max Activating Token Index: 119

Text #13

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7753. Min Act: 0.0000

Data Index: 1362615 (The Pile)

Max Activating Token Index: 871

Text #14

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.8951. Min Act: -0.0000

Data Index: 1628948 (The Pile)

Max Activating Token Index: 914

Text #15

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7814. Min Act: -0.0000

Data Index: 430415 (The Pile)

Max Activating Token Index: 444

Text #16

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7272. Min Act: -0.0000

Data Index: 1414965 (The Pile)

Max Activating Token Index: 283

Text #17

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7592. Min Act: -0.0000

Data Index: 1452652 (The Pile)

Max Activating Token Index: 639

Text #18

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7476. Min Act: -0.0000

Data Index: 122520 (The Pile)

Max Activating Token Index: 825

Text #19

Max Range: 1.2781. Min Range: -1.2781

Max Act: 0.7178. Min Act: -0.0000

Data Index: 867546 (The Pile)

Max Activating Token Index: 934