< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 76 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.4834. Min Act: -0.1675

Data Index: 121502 (The Pile)

Max Activating Token Index: 329

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2795. Min Act: -0.1699

Data Index: 458749 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2795. Min Act: -0.1700

Data Index: 9949636 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2795. Min Act: -0.1699

Data Index: 3363360 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2795. Min Act: -0.1331

Data Index: 643152 (The Pile)

Max Activating Token Index: 432

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2637. Min Act: -0.1434

Data Index: 9190160 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2480. Min Act: -0.1700

Data Index: 10296004 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2480. Min Act: -0.1331

Data Index: 1322432 (The Pile)

Max Activating Token Index: 135

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2480. Min Act: -0.1699

Data Index: 2193501 (The Pile)

Max Activating Token Index: 831

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2480. Min Act: -0.1660

Data Index: 7613905 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2480. Min Act: -0.1699

Data Index: 8021796 (The Pile)

Max Activating Token Index: 214

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2323. Min Act: -0.1700

Data Index: 8118273 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2323. Min Act: -0.1699

Data Index: 2783313 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2323. Min Act: -0.1700

Data Index: 2047376 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2323. Min Act: -0.1700

Data Index: 9192054 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2323. Min Act: -0.1699

Data Index: 4958494 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2166. Min Act: -0.1699

Data Index: 1764236 (The Pile)

Max Activating Token Index: 612

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2166. Min Act: -0.1700

Data Index: 4007316 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2008. Min Act: -0.1699

Data Index: 9134348 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4834. Min Range: -3.4834

Max Act: 3.2008. Min Act: -0.1699

Data Index: 653241 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #19