< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 43 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.0001. Min Range: -4.0001

Max Act: 4.0001. Min Act: -0.1700

Data Index: 6014437 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0001. Min Range: -4.0001

Max Act: 4.0001. Min Act: -0.1700

Data Index: 3668326 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9689. Min Act: -0.1700

Data Index: 7793569 (The Pile)

Max Activating Token Index: 713

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9689. Min Act: -0.1700

Data Index: 9998220 (The Pile)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9376. Min Act: -0.1700

Data Index: 193875 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9376. Min Act: -0.1700

Data Index: 4767215 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9063. Min Act: -0.1700

Data Index: 5489356 (The Pile)

Max Activating Token Index: 189

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9063. Min Act: -0.1700

Data Index: 638703 (The Pile)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9063. Min Act: -0.1700

Data Index: 5533820 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.9063. Min Act: -0.1700

Data Index: 7525685 (The Pile)

Max Activating Token Index: 928

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8751. Min Act: -0.1700

Data Index: 10733229 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8438. Min Act: -0.1700

Data Index: 16379 (The Pile)

Max Activating Token Index: 488

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8438. Min Act: -0.1700

Data Index: 4858423 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8125. Min Act: -0.1700

Data Index: 3787003 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8125. Min Act: -0.1700

Data Index: 1952667 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8125. Min Act: -0.1700

Data Index: 3559935 (The Pile)

Max Activating Token Index: 562

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8125. Min Act: -0.1700

Data Index: 6266837 (The Pile)

Max Activating Token Index: 778

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.8125. Min Act: -0.1700

Data Index: 5047869 (The Pile)

Max Activating Token Index: 933

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.7812. Min Act: -0.1700

Data Index: 1514285 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0001. Min Range: -4.0001

Max Act: 3.7812. Min Act: -0.1700

Data Index: 2012565 (The Pile)

Max Activating Token Index: 87

Click toggle to see full text

Truncated

Full Text #19