< Prev | Home | Model | Random | Next >

Model: SoLU Model: 6 Layers, 3072 Neurons per Layer

Dataset: The Pile

Neuron 2337 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('solu-6l-pile')



Text #0

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1782. Min Act: -0.0001

Data Index: 1599986 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1821. Min Act: -0.0001

Data Index: 1707898 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1693. Min Act: -0.0001

Data Index: 1281977 (The Pile)

Max Activating Token Index: 870

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1623. Min Act: -0.0001

Data Index: 1118198 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1612. Min Act: -0.0001

Data Index: 947375 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1605. Min Act: -0.0001

Data Index: 389588 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1597. Min Act: -0.0001

Data Index: 765274 (The Pile)

Max Activating Token Index: 876

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1556. Min Act: -0.0001

Data Index: 343687 (The Pile)

Max Activating Token Index: 911

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1528. Min Act: -0.0001

Data Index: 725439 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1602. Min Act: -0.0001

Data Index: 1346871 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1542. Min Act: -0.0001

Data Index: 805794 (The Pile)

Max Activating Token Index: 854

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1597. Min Act: -0.0001

Data Index: 1715799 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1552. Min Act: -0.0001

Data Index: 1867835 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1527. Min Act: -0.0001

Data Index: 653949 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1528. Min Act: -0.0001

Data Index: 1649829 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1535. Min Act: -0.0001

Data Index: 905257 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1487. Min Act: -0.0001

Data Index: 956853 (The Pile)

Max Activating Token Index: 896

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1528. Min Act: -0.0001

Data Index: 132247 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1471. Min Act: -0.0001

Data Index: 774974 (The Pile)

Max Activating Token Index: 935

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 0.1821. Min Range: -0.1821

Max Act: 0.1467. Min Act: -0.0001

Data Index: 1396681 (The Pile)

Max Activating Token Index: 901

Click toggle to see full text

Truncated

Full Text #19