< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4080 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.4729. Min Act: -0.1700

Data Index: 6392402 (The Pile)

Max Activating Token Index: 869

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.4104. Min Act: -0.1700

Data Index: 9549382 (The Pile)

Max Activating Token Index: 372

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.3167. Min Act: -0.1699

Data Index: 3429018 (The Pile)

Max Activating Token Index: 360

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.2854. Min Act: -0.1700

Data Index: 2392015 (The Pile)

Max Activating Token Index: 229

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.2542. Min Act: -0.1699

Data Index: 1563577 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.2229. Min Act: -0.1698

Data Index: 6744556 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.2229. Min Act: -0.1700

Data Index: 6325416 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.2229. Min Act: -0.1699

Data Index: 4589080 (The Pile)

Max Activating Token Index: 198

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1917. Min Act: -0.1700

Data Index: 2769019 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1917. Min Act: -0.1700

Data Index: 2693376 (The Pile)

Max Activating Token Index: 994

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1917. Min Act: -0.1700

Data Index: 3283186 (The Pile)

Max Activating Token Index: 506

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1917. Min Act: -0.1700

Data Index: 8646938 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1700

Data Index: 999151 (The Pile)

Max Activating Token Index: 524

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1700

Data Index: 10437339 (The Pile)

Max Activating Token Index: 437

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1699

Data Index: 3742032 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1699

Data Index: 1335720 (The Pile)

Max Activating Token Index: 806

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1699

Data Index: 8020520 (The Pile)

Max Activating Token Index: 206

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1700

Data Index: 7339751 (The Pile)

Max Activating Token Index: 686

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1700

Data Index: 5328922 (The Pile)

Max Activating Token Index: 863

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.4729. Min Range: -6.4729

Max Act: 6.1604. Min Act: -0.1698

Data Index: 1562646 (The Pile)

Max Activating Token Index: 574

Click toggle to see full text

Truncated

Full Text #19