< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 60 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: 4.8649. Min Range: -4.8649

Max Act: 4.8337. Min Act: -0.1656

Data Index: 212490 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.8649. Min Act: -0.1700

Data Index: 386551 (The Pile)

Max Activating Token Index: 273

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 4564979 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.8337. Min Act: -0.1699

Data Index: 3259424 (The Pile)

Max Activating Token Index: 45

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.8024. Min Act: -0.1700

Data Index: 6023186 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 9717237 (The Pile)

Max Activating Token Index: 910

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7087. Min Act: -0.1700

Data Index: 6608229 (The Pile)

Max Activating Token Index: 326

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 1880545 (The Pile)

Max Activating Token Index: 119

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 3859182 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 3696228 (The Pile)

Max Activating Token Index: 952

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7399. Min Act: -0.1700

Data Index: 373938 (The Pile)

Max Activating Token Index: 589

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.6774. Min Act: -0.1700

Data Index: 6812857 (The Pile)

Max Activating Token Index: 487

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 7254070 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7087. Min Act: -0.1700

Data Index: 1489667 (The Pile)

Max Activating Token Index: 343

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.6462. Min Act: -0.1700

Data Index: 7022363 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7712. Min Act: -0.1700

Data Index: 7047992 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.6462. Min Act: -0.1699

Data Index: 3393259 (The Pile)

Max Activating Token Index: 436

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7087. Min Act: -0.1700

Data Index: 6130523 (The Pile)

Max Activating Token Index: 754

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.7399. Min Act: -0.1700

Data Index: 7049271 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.8649. Min Range: -4.8649

Max Act: 4.6462. Min Act: -0.1451

Data Index: 3133921 (The Pile)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #19