< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 39 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.3253. Min Act: -0.1700

Data Index: 3430257 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1377. Min Act: -0.1700

Data Index: 9090207 (The Pile)

Max Activating Token Index: 91

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1377. Min Act: -0.1700

Data Index: 113815 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 6253986 (The Pile)

Max Activating Token Index: 292

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 10056388 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 9478541 (The Pile)

Max Activating Token Index: 867

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 5644504 (The Pile)

Max Activating Token Index: 658

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 4821445 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 1104235 (The Pile)

Max Activating Token Index: 435

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 7728586 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 9590300 (The Pile)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.1065. Min Act: -0.1700

Data Index: 8222918 (The Pile)

Max Activating Token Index: 788

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0752. Min Act: -0.1700

Data Index: 486777 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0752. Min Act: -0.1700

Data Index: 337587 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0752. Min Act: -0.1700

Data Index: 6181116 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0752. Min Act: -0.1700

Data Index: 7482601 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0440. Min Act: -0.1700

Data Index: 1323197 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0440. Min Act: -0.1700

Data Index: 5533793 (The Pile)

Max Activating Token Index: 30

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0440. Min Act: -0.1700

Data Index: 6000695 (The Pile)

Max Activating Token Index: 759

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3253. Min Range: -4.3253

Max Act: 4.0127. Min Act: -0.1700

Data Index: 5989161 (The Pile)

Max Activating Token Index: 336

Click toggle to see full text

Truncated

Full Text #19