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

Dataset: The Pile

Neuron 2649 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: 1.7617. Min Range: -1.7617

Max Act: 1.7617. Min Act: -0.0000

Data Index: 968796 (The Pile)

Max Activating Token Index: 700

Text #1

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.1398. Min Act: -0.0000

Data Index: 1857991 (The Pile)

Max Activating Token Index: 773

Text #2

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.1265. Min Act: -0.0000

Data Index: 1040920 (The Pile)

Max Activating Token Index: 574

Text #3

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.1029. Min Act: -0.0000

Data Index: 1570835 (The Pile)

Max Activating Token Index: 397

Text #4

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.1023. Min Act: -0.0000

Data Index: 20157 (The Pile)

Max Activating Token Index: 408

Text #5

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.1496. Min Act: -0.0000

Data Index: 441088 (The Pile)

Max Activating Token Index: 886

Text #6

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.0680. Min Act: -0.0000

Data Index: 1217289 (The Pile)

Max Activating Token Index: 422

Text #7

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.0613. Min Act: -0.0000

Data Index: 1141441 (The Pile)

Max Activating Token Index: 1015

Text #8

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.0467. Min Act: 0.0000

Data Index: 1594270 (The Pile)

Max Activating Token Index: 512

Text #9

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9816. Min Act: -0.0000

Data Index: 1065156 (The Pile)

Max Activating Token Index: 228

Text #10

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.0389. Min Act: -0.0000

Data Index: 1013303 (The Pile)

Max Activating Token Index: 785

Text #11

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9907. Min Act: 0.0001

Data Index: 751601 (The Pile)

Max Activating Token Index: 312

Text #12

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9217. Min Act: -0.0000

Data Index: 1626453 (The Pile)

Max Activating Token Index: 477

Text #13

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9695. Min Act: -0.0000

Data Index: 1500613 (The Pile)

Max Activating Token Index: 709

Text #14

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9664. Min Act: -0.0000

Data Index: 245646 (The Pile)

Max Activating Token Index: 897

Text #15

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9580. Min Act: -0.0000

Data Index: 1779242 (The Pile)

Max Activating Token Index: 521

Text #16

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9651. Min Act: -0.0000

Data Index: 504246 (The Pile)

Max Activating Token Index: 685

Text #17

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.9563. Min Act: -0.0000

Data Index: 1124891 (The Pile)

Max Activating Token Index: 510

Text #18

Max Range: 1.7617. Min Range: -1.7617

Max Act: 1.0024. Min Act: -0.0000

Data Index: 67487 (The Pile)

Max Activating Token Index: 843

Text #19

Max Range: 1.7617. Min Range: -1.7617

Max Act: 0.8836. Min Act: -0.0000

Data Index: 1236712 (The Pile)

Max Activating Token Index: 824