< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 8 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.2770. Min Act: -0.1700

Data Index: 9631263 (The Pile)

Max Activating Token Index: 815

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.2141. Min Act: -0.1700

Data Index: 6390136 (The Pile)

Max Activating Token Index: 799

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1827. Min Act: -0.1700

Data Index: 3109223 (The Pile)

Max Activating Token Index: 877

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1827. Min Act: -0.1700

Data Index: 10572670 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1827. Min Act: -0.1700

Data Index: 5459817 (The Pile)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1827. Min Act: -0.1700

Data Index: 8721410 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1669. Min Act: -0.1700

Data Index: 9285571 (The Pile)

Max Activating Token Index: 740

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1669. Min Act: -0.1700

Data Index: 3231013 (The Pile)

Max Activating Token Index: 609

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1354. Min Act: -0.1700

Data Index: 7674973 (The Pile)

Max Activating Token Index: 601

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1354. Min Act: -0.1700

Data Index: 1911082 (The Pile)

Max Activating Token Index: 958

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1197. Min Act: -0.1700

Data Index: 2983411 (The Pile)

Max Activating Token Index: 895

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.1197. Min Act: -0.1700

Data Index: 8043295 (The Pile)

Max Activating Token Index: 385

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0881. Min Act: -0.1700

Data Index: 8062556 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0724. Min Act: -0.1700

Data Index: 2419534 (The Pile)

Max Activating Token Index: 588

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0566. Min Act: -0.1700

Data Index: 5022451 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0566. Min Act: -0.1700

Data Index: 2525027 (The Pile)

Max Activating Token Index: 353

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0566. Min Act: -0.1700

Data Index: 2341884 (The Pile)

Max Activating Token Index: 508

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0408. Min Act: -0.1700

Data Index: 5164747 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0408. Min Act: -0.1700

Data Index: 9942396 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2770. Min Range: -3.2770

Max Act: 3.0408. Min Act: -0.1700

Data Index: 4103094 (The Pile)

Max Activating Token Index: 610

Click toggle to see full text

Truncated

Full Text #19