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

Dataset: The Pile

Neuron 1319 in Layer 6

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.8065. Min Act: -0.0000

Data Index: 233935 (The Pile)

Max Activating Token Index: 227

Text #1

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.8028. Min Act: -0.0000

Data Index: 1587210 (The Pile)

Max Activating Token Index: 388

Text #2

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7658. Min Act: -0.0000

Data Index: 1046569 (The Pile)

Max Activating Token Index: 652

Text #3

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6738. Min Act: -0.0000

Data Index: 1897091 (The Pile)

Max Activating Token Index: 198

Text #4

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6837. Min Act: -0.0000

Data Index: 785017 (The Pile)

Max Activating Token Index: 224

Text #5

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.7585. Min Act: -0.0000

Data Index: 394690 (The Pile)

Max Activating Token Index: 601

Text #6

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6461. Min Act: -0.0000

Data Index: 1122568 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6829. Min Act: -0.0000

Data Index: 1805395 (The Pile)

Max Activating Token Index: 428

Text #8

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6732. Min Act: -0.0000

Data Index: 834737 (The Pile)

Max Activating Token Index: 286

Text #9

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6378. Min Act: -0.0000

Data Index: 1861287 (The Pile)

Max Activating Token Index: 601

Text #10

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5893. Min Act: -0.0000

Data Index: 886460 (The Pile)

Max Activating Token Index: 790

Text #11

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6178. Min Act: -0.0000

Data Index: 800773 (The Pile)

Max Activating Token Index: 563

Text #12

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5939. Min Act: -0.0000

Data Index: 1936808 (The Pile)

Max Activating Token Index: 989

Text #13

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5992. Min Act: -0.0000

Data Index: 636420 (The Pile)

Max Activating Token Index: 479

Text #14

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5918. Min Act: -0.0000

Data Index: 1949875 (The Pile)

Max Activating Token Index: 974

Text #15

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6403. Min Act: -0.0000

Data Index: 1557329 (The Pile)

Max Activating Token Index: 951

Text #16

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6042. Min Act: -0.0000

Data Index: 524556 (The Pile)

Max Activating Token Index: 892

Text #17

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6002. Min Act: -0.0000

Data Index: 383486 (The Pile)

Max Activating Token Index: 602

Text #18

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.5810. Min Act: -0.0000

Data Index: 821193 (The Pile)

Max Activating Token Index: 744

Text #19

Max Range: 0.8065. Min Range: -0.8065

Max Act: 0.6356. Min Act: -0.0000

Data Index: 90001 (The Pile)

Max Activating Token Index: 674