< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-350m')



Text #0

Max Range: 75.6360. Min Range: -75.6360

Max Act: 75.6360. Min Act: -0.0033

Data Index: 6631926 (The Pile)

Max Activating Token Index: 173

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 75.6360. Min Range: -75.6360

Max Act: 58.8860. Min Act: -0.0026

Data Index: 8895737 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 75.6360. Min Range: -75.6360

Max Act: 57.8860. Min Act: -0.0000

Data Index: 2808986 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 75.6360. Min Range: -75.6360

Max Act: 56.3860. Min Act: -0.1689

Data Index: 9717289 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.6360. Min Act: -0.0000

Data Index: 5632461 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.6360. Min Act: -0.0008

Data Index: 7431195 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.3860. Min Act: -0.1392

Data Index: 7597754 (The Pile)

Max Activating Token Index: 717

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.1360. Min Act: -0.0000

Data Index: 10678914 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.1360. Min Act: -0.0000

Data Index: 6739026 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.1360. Min Act: -0.0000

Data Index: 7184888 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 75.6360. Min Range: -75.6360

Max Act: 52.1360. Min Act: -0.0000

Data Index: 1891479 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 75.6360. Min Range: -75.6360

Max Act: 51.6360. Min Act: -0.0000

Data Index: 7469644 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 75.6360. Min Range: -75.6360

Max Act: 50.3860. Min Act: -0.1667

Data Index: 8520094 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 75.6360. Min Range: -75.6360

Max Act: 50.3860. Min Act: -0.1667

Data Index: 7942650 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 75.6360. Min Range: -75.6360

Max Act: 50.1360. Min Act: -0.0000

Data Index: 2080783 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 75.6360. Min Range: -75.6360

Max Act: 49.6360. Min Act: -0.0000

Data Index: 7051538 (The Pile)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 75.6360. Min Range: -75.6360

Max Act: 49.3860. Min Act: -0.0000

Data Index: 5783061 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 75.6360. Min Range: -75.6360

Max Act: 49.3860. Min Act: -0.1586

Data Index: 6582500 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 75.6360. Min Range: -75.6360

Max Act: 48.6360. Min Act: -0.0000

Data Index: 1189446 (The Pile)

Max Activating Token Index: 4

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 75.6360. Min Range: -75.6360

Max Act: 48.6360. Min Act: -0.0000

Data Index: 601640 (The Pile)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #19