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

Dataset: The Pile

Neuron 1872 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: 0.1686. Min Range: -0.1686

Max Act: 0.1686. Min Act: -0.0000

Data Index: 575995 (The Pile)

Max Activating Token Index: 320

Text #1

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1584. Min Act: -0.0000

Data Index: 1337409 (The Pile)

Max Activating Token Index: 167

Text #2

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1571. Min Act: -0.0000

Data Index: 715981 (The Pile)

Max Activating Token Index: 624

Text #3

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1591. Min Act: -0.0000

Data Index: 56564 (The Pile)

Max Activating Token Index: 569

Text #4

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1678. Min Act: -0.0000

Data Index: 599141 (The Pile)

Max Activating Token Index: 817

Text #5

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1766889 (The Pile)

Max Activating Token Index: 276

Text #6

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1419. Min Act: -0.0000

Data Index: 1392737 (The Pile)

Max Activating Token Index: 857

Text #7

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1499. Min Act: -0.0000

Data Index: 1558574 (The Pile)

Max Activating Token Index: 179

Text #8

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1512. Min Act: -0.0000

Data Index: 774905 (The Pile)

Max Activating Token Index: 868

Text #9

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1529. Min Act: -0.0000

Data Index: 771685 (The Pile)

Max Activating Token Index: 420

Text #10

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1528. Min Act: -0.0000

Data Index: 1311528 (The Pile)

Max Activating Token Index: 842

Text #11

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1503. Min Act: -0.0000

Data Index: 565023 (The Pile)

Max Activating Token Index: 210

Text #12

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1503. Min Act: -0.0000

Data Index: 113866 (The Pile)

Max Activating Token Index: 148

Text #13

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1472. Min Act: -0.0000

Data Index: 165332 (The Pile)

Max Activating Token Index: 480

Text #14

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1464. Min Act: -0.0000

Data Index: 791059 (The Pile)

Max Activating Token Index: 501

Text #15

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1516. Min Act: -0.0000

Data Index: 1507318 (The Pile)

Max Activating Token Index: 332

Text #16

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1474. Min Act: -0.0000

Data Index: 1478679 (The Pile)

Max Activating Token Index: 181

Text #17

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1417. Min Act: -0.0000

Data Index: 291509 (The Pile)

Max Activating Token Index: 511

Text #18

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1436. Min Act: -0.0000

Data Index: 1551785 (The Pile)

Max Activating Token Index: 655

Text #19

Max Range: 0.1686. Min Range: -0.1686

Max Act: 0.1456. Min Act: -0.0000

Data Index: 1173963 (The Pile)

Max Activating Token Index: 77