< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 24 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.3501. Min Act: -0.1700

Data Index: 3729180 (The Pile)

Max Activating Token Index: 839

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.2876. Min Act: -0.1700

Data Index: 2431770 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.2251. Min Act: -0.1700

Data Index: 3388714 (The Pile)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.1938. Min Act: -0.1700

Data Index: 5475603 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.1001. Min Act: -0.1700

Data Index: 1782251 (The Pile)

Max Activating Token Index: 881

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.0063. Min Act: -0.1700

Data Index: 2910443 (The Pile)

Max Activating Token Index: 673

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 7.3501. Min Range: -7.3501

Max Act: 7.0063. Min Act: -0.1700

Data Index: 8920989 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9751. Min Act: -0.1700

Data Index: 4062430 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9438. Min Act: -0.1700

Data Index: 1224850 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9438. Min Act: -0.1700

Data Index: 2273117 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9438. Min Act: -0.1700

Data Index: 6789196 (The Pile)

Max Activating Token Index: 842

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9126. Min Act: -0.1700

Data Index: 8208796 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9126. Min Act: -0.1700

Data Index: 1498664 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.9126. Min Act: -0.1700

Data Index: 6070319 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.8813. Min Act: -0.1700

Data Index: 9566081 (The Pile)

Max Activating Token Index: 763

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.8813. Min Act: -0.1700

Data Index: 10199453 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.8813. Min Act: -0.1700

Data Index: 3928597 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.8813. Min Act: -0.1700

Data Index: 3821247 (The Pile)

Max Activating Token Index: 79

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.8501. Min Act: -0.1700

Data Index: 2386261 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 7.3501. Min Range: -7.3501

Max Act: 6.8501. Min Act: -0.1700

Data Index: 3836088 (The Pile)

Max Activating Token Index: 702

Click toggle to see full text

Truncated

Full Text #19