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

Dataset: The Pile

Neuron 3935 in Layer 0

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-10l-pile')

Text #0

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0644. Min Act: 0.0000

Data Index: 1002279 (The Pile)

Max Activating Token Index: 14

Text #1

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0595. Min Act: 0.0000

Data Index: 110364 (The Pile)

Max Activating Token Index: 20

Text #2

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0568. Min Act: 0.0000

Data Index: 1567044 (The Pile)

Max Activating Token Index: 8

Text #3

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0566. Min Act: 0.0000

Data Index: 521204 (The Pile)

Max Activating Token Index: 76

Text #4

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0585. Min Act: 0.0000

Data Index: 1853587 (The Pile)

Max Activating Token Index: 43

Text #5

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0553. Min Act: 0.0000

Data Index: 293529 (The Pile)

Max Activating Token Index: 18

Text #6

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0538. Min Act: 0.0000

Data Index: 212808 (The Pile)

Max Activating Token Index: 29

Text #7

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0529. Min Act: 0.0000

Data Index: 213069 (The Pile)

Max Activating Token Index: 10

Text #8

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0524. Min Act: 0.0000

Data Index: 1553838 (The Pile)

Max Activating Token Index: 6

Text #9

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0521. Min Act: -0.0000

Data Index: 863535 (The Pile)

Max Activating Token Index: 7

Text #10

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0503. Min Act: -0.0000

Data Index: 1728470 (The Pile)

Max Activating Token Index: 36

Text #11

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0519. Min Act: 0.0000

Data Index: 1465781 (The Pile)

Max Activating Token Index: 35

Text #12

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0518. Min Act: 0.0000

Data Index: 549330 (The Pile)

Max Activating Token Index: 51

Text #13

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0515. Min Act: 0.0000

Data Index: 489802 (The Pile)

Max Activating Token Index: 14

Text #14

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0510. Min Act: 0.0000

Data Index: 1529003 (The Pile)

Max Activating Token Index: 332

Text #15

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0507. Min Act: 0.0000

Data Index: 564808 (The Pile)

Max Activating Token Index: 8

Text #16

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0507. Min Act: 0.0000

Data Index: 1145367 (The Pile)

Max Activating Token Index: 6

Text #17

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0487. Min Act: -0.0000

Data Index: 1480185 (The Pile)

Max Activating Token Index: 14

Text #18

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1395135 (The Pile)

Max Activating Token Index: 63

Text #19

Max Range: 0.0644. Min Range: -0.0644

Max Act: 0.0504. Min Act: -0.0000

Data Index: 1309201 (The Pile)

Max Activating Token Index: 12