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

Dataset: The Pile

Neuron 96 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1508. Min Act: 0.0000

Data Index: 71814 (The Pile)

Max Activating Token Index: 148

Text #1

Max Range: 1.1769. Min Range: -1.1769

Max Act: 1.1769. Min Act: 0.0000

Data Index: 68937 (The Pile)

Max Activating Token Index: 753

Text #2

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.9429. Min Act: -0.0000

Data Index: 1234537 (The Pile)

Max Activating Token Index: 873

Text #3

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8636. Min Act: -0.0000

Data Index: 413848 (The Pile)

Max Activating Token Index: 652

Text #4

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8247. Min Act: -0.0000

Data Index: 1184397 (The Pile)

Max Activating Token Index: 661

Text #5

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7995. Min Act: -0.0000

Data Index: 1343595 (The Pile)

Max Activating Token Index: 873

Text #6

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8785. Min Act: -0.0000

Data Index: 1856779 (The Pile)

Max Activating Token Index: 988

Text #7

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7836. Min Act: 0.0000

Data Index: 1424550 (The Pile)

Max Activating Token Index: 130

Text #8

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.8070. Min Act: -0.0000

Data Index: 780199 (The Pile)

Max Activating Token Index: 414

Text #9

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7894. Min Act: -0.0000

Data Index: 1895796 (The Pile)

Max Activating Token Index: 629

Text #10

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7486. Min Act: -0.0000

Data Index: 1825204 (The Pile)

Max Activating Token Index: 538

Text #11

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7349. Min Act: -0.0000

Data Index: 634143 (The Pile)

Max Activating Token Index: 428

Text #12

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7223. Min Act: -0.0000

Data Index: 1543758 (The Pile)

Max Activating Token Index: 241

Text #13

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7105. Min Act: 0.0000

Data Index: 1235788 (The Pile)

Max Activating Token Index: 206

Text #14

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.7011. Min Act: -0.0000

Data Index: 1290921 (The Pile)

Max Activating Token Index: 452

Text #15

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6522. Min Act: -0.0000

Data Index: 227351 (The Pile)

Max Activating Token Index: 237

Text #16

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6722. Min Act: 0.0000

Data Index: 1719606 (The Pile)

Max Activating Token Index: 738

Text #17

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6306. Min Act: -0.0000

Data Index: 364777 (The Pile)

Max Activating Token Index: 490

Text #18

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6652. Min Act: -0.0000

Data Index: 1389699 (The Pile)

Max Activating Token Index: 542

Text #19

Max Range: 1.1769. Min Range: -1.1769

Max Act: 0.6118. Min Act: -0.0000

Data Index: 1598934 (The Pile)

Max Activating Token Index: 345