< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1083 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: 2.5502. Min Range: -2.5502

Max Act: 2.5502. Min Act: -0.1700

Data Index: 3383487 (The Pile)

Max Activating Token Index: 35

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4855. Min Act: -0.1700

Data Index: 57165 (The Pile)

Max Activating Token Index: 36

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4855. Min Act: -0.1700

Data Index: 10759768 (The Pile)

Max Activating Token Index: 595

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4855. Min Act: -0.1700

Data Index: 197572 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4368. Min Act: -0.1700

Data Index: 5219949 (The Pile)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4693. Min Act: -0.1700

Data Index: 10261369 (The Pile)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4368. Min Act: -0.1700

Data Index: 3186904 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4368. Min Act: -0.1700

Data Index: 9473347 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4531. Min Act: -0.1700

Data Index: 8745727 (The Pile)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4531. Min Act: -0.1700

Data Index: 7365726 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4368. Min Act: -0.1700

Data Index: 8653002 (The Pile)

Max Activating Token Index: 278

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4205. Min Act: -0.1700

Data Index: 6309430 (The Pile)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4368. Min Act: -0.1700

Data Index: 2784182 (The Pile)

Max Activating Token Index: 748

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4043. Min Act: -0.1700

Data Index: 1509955 (The Pile)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4368. Min Act: -0.1700

Data Index: 6891622 (The Pile)

Max Activating Token Index: 579

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4205. Min Act: -0.1700

Data Index: 6207529 (The Pile)

Max Activating Token Index: 948

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4205. Min Act: -0.1699

Data Index: 5242852 (The Pile)

Max Activating Token Index: 975

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.3879. Min Act: -0.1700

Data Index: 4365282 (The Pile)

Max Activating Token Index: 987

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.4205. Min Act: -0.1700

Data Index: 3423310 (The Pile)

Max Activating Token Index: 466

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.5502. Min Range: -2.5502

Max Act: 2.3879. Min Act: -0.1700

Data Index: 1044226 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #19