< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1129 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.2044. Min Act: -0.1700

Data Index: 4193423 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1887. Min Act: -0.1700

Data Index: 10519113 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1572. Min Act: -0.1700

Data Index: 8332524 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1572. Min Act: -0.1700

Data Index: 8849248 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1730. Min Act: -0.1700

Data Index: 2082902 (The Pile)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1257. Min Act: -0.1700

Data Index: 1355015 (The Pile)

Max Activating Token Index: 824

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1257. Min Act: -0.1700

Data Index: 2434767 (The Pile)

Max Activating Token Index: 509

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1415. Min Act: -0.1700

Data Index: 3375929 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1100. Min Act: -0.1700

Data Index: 10736746 (The Pile)

Max Activating Token Index: 207

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1257. Min Act: -0.1700

Data Index: 7253552 (The Pile)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0942. Min Act: -0.1700

Data Index: 22623 (The Pile)

Max Activating Token Index: 586

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0942. Min Act: -0.1700

Data Index: 10587066 (The Pile)

Max Activating Token Index: 261

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1100. Min Act: -0.1700

Data Index: 6425927 (The Pile)

Max Activating Token Index: 1007

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0469. Min Act: -0.1700

Data Index: 3065695 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0784. Min Act: -0.1700

Data Index: 4177790 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1257. Min Act: -0.1700

Data Index: 10653895 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0626. Min Act: -0.1700

Data Index: 9190660 (The Pile)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.1100. Min Act: -0.1700

Data Index: 6328194 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0626. Min Act: -0.1700

Data Index: 7437268 (The Pile)

Max Activating Token Index: 323

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2044. Min Range: -3.2044

Max Act: 3.0469. Min Act: -0.1700

Data Index: 499217 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #19