< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1060 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: 3.2820. Min Range: -3.2820

Max Act: 3.2820. Min Act: -0.1700

Data Index: 6527494 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.2348. Min Act: -0.1700

Data Index: 543499 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.2505. Min Act: -0.1700

Data Index: 1550258 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.2191. Min Act: -0.1700

Data Index: 4439994 (The Pile)

Max Activating Token Index: 522

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.2034. Min Act: -0.1700

Data Index: 8362813 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.2191. Min Act: -0.1700

Data Index: 2444203 (The Pile)

Max Activating Token Index: 1014

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1719. Min Act: -0.1700

Data Index: 2079127 (The Pile)

Max Activating Token Index: 527

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1719. Min Act: -0.1700

Data Index: 2248430 (The Pile)

Max Activating Token Index: 394

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1719. Min Act: -0.1700

Data Index: 4330321 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1561. Min Act: -0.1700

Data Index: 10406254 (The Pile)

Max Activating Token Index: 760

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1404. Min Act: -0.1700

Data Index: 5934703 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1561. Min Act: -0.1700

Data Index: 6257869 (The Pile)

Max Activating Token Index: 1010

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1561. Min Act: -0.1700

Data Index: 3220083 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1404. Min Act: -0.1700

Data Index: 1109142 (The Pile)

Max Activating Token Index: 977

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1246. Min Act: -0.1700

Data Index: 7541411 (The Pile)

Max Activating Token Index: 379

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1246. Min Act: -0.1700

Data Index: 8018415 (The Pile)

Max Activating Token Index: 947

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1246. Min Act: -0.1700

Data Index: 124043 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1404. Min Act: -0.1700

Data Index: 8551409 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.1246. Min Act: -0.1700

Data Index: 4826136 (The Pile)

Max Activating Token Index: 109

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2820. Min Range: -3.2820

Max Act: 3.0773. Min Act: -0.1700

Data Index: 3162310 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #19