< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1996 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: 3.4394. Min Range: -3.4394

Max Act: 3.3139. Min Act: -0.1511

Data Index: 3065227 (The Pile)

Max Activating Token Index: 991

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.4394. Min Act: -0.1615

Data Index: 10321388 (The Pile)

Max Activating Token Index: 903

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.4080. Min Act: -0.1700

Data Index: 861874 (The Pile)

Max Activating Token Index: 94

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1409. Min Act: -0.1700

Data Index: 7374927 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.3610. Min Act: -0.1699

Data Index: 617095 (The Pile)

Max Activating Token Index: 785

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.4080. Min Act: -0.1700

Data Index: 7126003 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.2667. Min Act: -0.1700

Data Index: 7586625 (The Pile)

Max Activating Token Index: 287

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1881. Min Act: -0.1661

Data Index: 487180 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1724. Min Act: -0.1700

Data Index: 8861956 (The Pile)

Max Activating Token Index: 68

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.2982. Min Act: -0.1700

Data Index: 8559893 (The Pile)

Max Activating Token Index: 546

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.2510. Min Act: -0.1700

Data Index: 1530930 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.2353. Min Act: -0.1699

Data Index: 610188 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1566. Min Act: -0.1700

Data Index: 8861979 (The Pile)

Max Activating Token Index: 767

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.2196. Min Act: -0.1700

Data Index: 6050295 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1094. Min Act: -0.1700

Data Index: 8380998 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1094. Min Act: -0.1700

Data Index: 6496897 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1881. Min Act: -0.1693

Data Index: 5614439 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.2510. Min Act: -0.1700

Data Index: 8831383 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.3139. Min Act: -0.1700

Data Index: 6241358 (The Pile)

Max Activating Token Index: 779

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.4394. Min Range: -3.4394

Max Act: 3.1881. Min Act: -0.1700

Data Index: 45207 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #19