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

Dataset: The Pile

Neuron 3574 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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

Text #0

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4732. Min Act: -0.0000

Data Index: 23135 (The Pile)

Max Activating Token Index: 954

Text #1

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4426. Min Act: -0.0000

Data Index: 695649 (The Pile)

Max Activating Token Index: 704

Text #2

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3976. Min Act: -0.0000

Data Index: 1935421 (The Pile)

Max Activating Token Index: 432

Text #3

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4218. Min Act: -0.0000

Data Index: 957774 (The Pile)

Max Activating Token Index: 815

Text #4

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3732. Min Act: -0.0000

Data Index: 319688 (The Pile)

Max Activating Token Index: 557

Text #5

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3529. Min Act: -0.0000

Data Index: 1515116 (The Pile)

Max Activating Token Index: 701

Text #6

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4759. Min Act: -0.0000

Data Index: 1039441 (The Pile)

Max Activating Token Index: 835

Text #7

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3674. Min Act: -0.0000

Data Index: 3879 (The Pile)

Max Activating Token Index: 909

Text #8

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3798. Min Act: -0.0000

Data Index: 1318552 (The Pile)

Max Activating Token Index: 315

Text #9

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4058. Min Act: -0.0000

Data Index: 1898297 (The Pile)

Max Activating Token Index: 160

Text #10

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3703. Min Act: -0.0000

Data Index: 1269896 (The Pile)

Max Activating Token Index: 945

Text #11

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.4074. Min Act: -0.0000

Data Index: 1482668 (The Pile)

Max Activating Token Index: 116

Text #12

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3608. Min Act: 0.0000

Data Index: 1732622 (The Pile)

Max Activating Token Index: 881

Text #13

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3424. Min Act: 0.0000

Data Index: 281969 (The Pile)

Max Activating Token Index: 363

Text #14

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3404. Min Act: -0.0000

Data Index: 1572057 (The Pile)

Max Activating Token Index: 884

Text #15

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3349. Min Act: -0.0000

Data Index: 1321423 (The Pile)

Max Activating Token Index: 77

Text #16

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3483. Min Act: 0.0000

Data Index: 775987 (The Pile)

Max Activating Token Index: 347

Text #17

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3358. Min Act: -0.0000

Data Index: 55314 (The Pile)

Max Activating Token Index: 338

Text #18

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3356. Min Act: -0.0000

Data Index: 545170 (The Pile)

Max Activating Token Index: 630

Text #19

Max Range: 0.4759. Min Range: -0.4759

Max Act: 0.3189. Min Act: -0.0000

Data Index: 1143083 (The Pile)

Max Activating Token Index: 754