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

Dataset: The Pile

Neuron 4479 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: 0.1762. Min Range: -0.1762

Max Act: 0.1762. Min Act: -0.0000

Data Index: 1808653 (The Pile)

Max Activating Token Index: 953

Text #1

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1750. Min Act: -0.0000

Data Index: 452294 (The Pile)

Max Activating Token Index: 850

Text #2

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1699. Min Act: -0.0000

Data Index: 383848 (The Pile)

Max Activating Token Index: 53

Text #3

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1509. Min Act: -0.0000

Data Index: 790902 (The Pile)

Max Activating Token Index: 308

Text #4

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1522. Min Act: -0.0000

Data Index: 1380014 (The Pile)

Max Activating Token Index: 223

Text #5

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1476. Min Act: -0.0000

Data Index: 133623 (The Pile)

Max Activating Token Index: 568

Text #6

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1500. Min Act: -0.0000

Data Index: 1171832 (The Pile)

Max Activating Token Index: 300

Text #7

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1210726 (The Pile)

Max Activating Token Index: 838

Text #8

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1401. Min Act: -0.0000

Data Index: 1506516 (The Pile)

Max Activating Token Index: 927

Text #9

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1425. Min Act: -0.0000

Data Index: 1646326 (The Pile)

Max Activating Token Index: 905

Text #10

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1347. Min Act: -0.0000

Data Index: 1038709 (The Pile)

Max Activating Token Index: 691

Text #11

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1371. Min Act: -0.0000

Data Index: 1774800 (The Pile)

Max Activating Token Index: 759

Text #12

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1356. Min Act: -0.0000

Data Index: 646638 (The Pile)

Max Activating Token Index: 821

Text #13

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1401. Min Act: -0.0000

Data Index: 604017 (The Pile)

Max Activating Token Index: 308

Text #14

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1348. Min Act: -0.0000

Data Index: 936760 (The Pile)

Max Activating Token Index: 660

Text #15

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1318. Min Act: 0.0000

Data Index: 1830125 (The Pile)

Max Activating Token Index: 453

Text #16

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1293. Min Act: -0.0000

Data Index: 821154 (The Pile)

Max Activating Token Index: 979

Text #17

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1325. Min Act: -0.0000

Data Index: 631093 (The Pile)

Max Activating Token Index: 37

Text #18

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1299. Min Act: -0.0000

Data Index: 572977 (The Pile)

Max Activating Token Index: 923

Text #19

Max Range: 0.1762. Min Range: -0.1762

Max Act: 0.1337. Min Act: -0.0000

Data Index: 1505783 (The Pile)

Max Activating Token Index: 84