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

Dataset: The Pile

Neuron 4383 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: 0.1912. Min Range: -0.1912

Max Act: 0.1912. Min Act: -0.0000

Data Index: 515824 (The Pile)

Max Activating Token Index: 785

Text #1

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1177383 (The Pile)

Max Activating Token Index: 881

Text #2

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1639. Min Act: -0.0000

Data Index: 1017611 (The Pile)

Max Activating Token Index: 836

Text #3

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1781. Min Act: -0.0000

Data Index: 1767373 (The Pile)

Max Activating Token Index: 881

Text #4

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1622. Min Act: -0.0000

Data Index: 1307937 (The Pile)

Max Activating Token Index: 569

Text #5

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1548. Min Act: -0.0000

Data Index: 192585 (The Pile)

Max Activating Token Index: 487

Text #6

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1567. Min Act: -0.0000

Data Index: 407680 (The Pile)

Max Activating Token Index: 736

Text #7

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1586. Min Act: -0.0000

Data Index: 1805014 (The Pile)

Max Activating Token Index: 949

Text #8

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1430. Min Act: -0.0000

Data Index: 971556 (The Pile)

Max Activating Token Index: 728

Text #9

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1579. Min Act: -0.0000

Data Index: 1474382 (The Pile)

Max Activating Token Index: 963

Text #10

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1453. Min Act: -0.0000

Data Index: 382573 (The Pile)

Max Activating Token Index: 935

Text #11

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1367. Min Act: -0.0000

Data Index: 844101 (The Pile)

Max Activating Token Index: 616

Text #12

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1446. Min Act: -0.0000

Data Index: 284372 (The Pile)

Max Activating Token Index: 744

Text #13

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1439. Min Act: -0.0000

Data Index: 2919 (The Pile)

Max Activating Token Index: 652

Text #14

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1435. Min Act: -0.0000

Data Index: 521733 (The Pile)

Max Activating Token Index: 185

Text #15

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1432. Min Act: -0.0000

Data Index: 1863921 (The Pile)

Max Activating Token Index: 64

Text #16

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1188. Min Act: -0.0000

Data Index: 1728426 (The Pile)

Max Activating Token Index: 538

Text #17

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1394. Min Act: -0.0000

Data Index: 1524358 (The Pile)

Max Activating Token Index: 920

Text #18

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1387. Min Act: -0.0000

Data Index: 867439 (The Pile)

Max Activating Token Index: 431

Text #19

Max Range: 0.1912. Min Range: -0.1912

Max Act: 0.1273. Min Act: -0.0000

Data Index: 1219498 (The Pile)

Max Activating Token Index: 340