< Prev | Home | Model | Random | Next >

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

Dataset: The Pile

Neuron 57 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: 2.1509. Min Range: -2.1509

Max Act: 2.1249. Min Act: -0.0000

Data Index: 1937851 (The Pile)

Max Activating Token Index: 61

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.9745. Min Act: -0.0000

Data Index: 1880053 (The Pile)

Max Activating Token Index: 922

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.1509. Min Range: -2.1509

Max Act: 2.1509. Min Act: -0.0000

Data Index: 181712 (The Pile)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.1509. Min Range: -2.1509

Max Act: 2.1246. Min Act: -0.0000

Data Index: 1558041 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.9519. Min Act: -0.0000

Data Index: 1232357 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.9369. Min Act: -0.0000

Data Index: 1425649 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.9320. Min Act: -0.0000

Data Index: 529510 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.8712. Min Act: -0.0000

Data Index: 754712 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.7512. Min Act: -0.0000

Data Index: 1268150 (The Pile)

Max Activating Token Index: 704

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.8396. Min Act: -0.0000

Data Index: 445282 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.9182. Min Act: -0.0000

Data Index: 1908825 (The Pile)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.8157. Min Act: -0.0000

Data Index: 697526 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.7633. Min Act: -0.0000

Data Index: 1496009 (The Pile)

Max Activating Token Index: 953

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.6993. Min Act: -0.0000

Data Index: 901082 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.6896. Min Act: -0.0000

Data Index: 1919213 (The Pile)

Max Activating Token Index: 44

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.7948. Min Act: -0.0000

Data Index: 72452 (The Pile)

Max Activating Token Index: 698

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.7865. Min Act: -0.0000

Data Index: 1098563 (The Pile)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.6507. Min Act: -0.0000

Data Index: 1884747 (The Pile)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.5636. Min Act: -0.0000

Data Index: 1483219 (The Pile)

Max Activating Token Index: 635

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.1509. Min Range: -2.1509

Max Act: 1.6475. Min Act: -0.0000

Data Index: 1306490 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #19