< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1915 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.1665. Min Act: -0.1700

Data Index: 204910 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.1665. Min Act: -0.1700

Data Index: 3918514 (The Pile)

Max Activating Token Index: 963

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.1352. Min Act: -0.1700

Data Index: 7405763 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.2290. Min Act: -0.1700

Data Index: 2103148 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.2603. Min Act: -0.1700

Data Index: 3796454 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.1040. Min Act: -0.1700

Data Index: 7229206 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.0727. Min Act: -0.1700

Data Index: 5998208 (The Pile)

Max Activating Token Index: 569

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.0102. Min Act: -0.1700

Data Index: 656735 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.8851. Min Act: -0.1700

Data Index: 1835939 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.1352. Min Act: -0.1700

Data Index: 1773274 (The Pile)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.7600. Min Act: -0.1700

Data Index: 8595323 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.0727. Min Act: -0.1700

Data Index: 8981007 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.1040. Min Act: -0.1700

Data Index: 9589680 (The Pile)

Max Activating Token Index: 632

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.0102. Min Act: -0.1700

Data Index: 6924656 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.2603. Min Range: -4.2603

Max Act: 4.0102. Min Act: -0.1700

Data Index: 6131506 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.9476. Min Act: -0.1700

Data Index: 7694262 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.8851. Min Act: -0.1700

Data Index: 4709495 (The Pile)

Max Activating Token Index: 660

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.8225. Min Act: -0.1700

Data Index: 3200135 (The Pile)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.8225. Min Act: -0.1700

Data Index: 8954980 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.2603. Min Range: -4.2603

Max Act: 3.9789. Min Act: -0.1700

Data Index: 3806893 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #19