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

Dataset: The Pile

Neuron 850 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: 0.1955. Min Range: -0.1955

Max Act: 0.1955. Min Act: -0.0000

Data Index: 249594 (The Pile)

Max Activating Token Index: 701

Text #1

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1903. Min Act: -0.0000

Data Index: 378590 (The Pile)

Max Activating Token Index: 42

Text #2

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1634. Min Act: -0.0000

Data Index: 1275105 (The Pile)

Max Activating Token Index: 395

Text #3

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1542. Min Act: -0.0000

Data Index: 1901811 (The Pile)

Max Activating Token Index: 872

Text #4

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1494. Min Act: -0.0000

Data Index: 436731 (The Pile)

Max Activating Token Index: 676

Text #5

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1651. Min Act: -0.0000

Data Index: 825081 (The Pile)

Max Activating Token Index: 951

Text #6

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1597. Min Act: -0.0000

Data Index: 635926 (The Pile)

Max Activating Token Index: 712

Text #7

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1825. Min Act: -0.0000

Data Index: 986030 (The Pile)

Max Activating Token Index: 619

Text #8

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1569. Min Act: -0.0000

Data Index: 881046 (The Pile)

Max Activating Token Index: 859

Text #9

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1484. Min Act: -0.0000

Data Index: 125178 (The Pile)

Max Activating Token Index: 943

Text #10

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1492. Min Act: -0.0000

Data Index: 960899 (The Pile)

Max Activating Token Index: 178

Text #11

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1374. Min Act: -0.0000

Data Index: 1521768 (The Pile)

Max Activating Token Index: 667

Text #12

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1428. Min Act: -0.0000

Data Index: 25539 (The Pile)

Max Activating Token Index: 577

Text #13

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1389. Min Act: -0.0000

Data Index: 246635 (The Pile)

Max Activating Token Index: 971

Text #14

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1385. Min Act: -0.0000

Data Index: 1457632 (The Pile)

Max Activating Token Index: 395

Text #15

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1471. Min Act: -0.0000

Data Index: 1857419 (The Pile)

Max Activating Token Index: 57

Text #16

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1399. Min Act: -0.0000

Data Index: 1548511 (The Pile)

Max Activating Token Index: 33

Text #17

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1360. Min Act: -0.0000

Data Index: 1007729 (The Pile)

Max Activating Token Index: 687

Text #18

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1304. Min Act: -0.0000

Data Index: 425720 (The Pile)

Max Activating Token Index: 442

Text #19

Max Range: 0.1955. Min Range: -0.1955

Max Act: 0.1365. Min Act: -0.0000

Data Index: 1714894 (The Pile)

Max Activating Token Index: 63