< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 46 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0543. Min Range: -3.0543

Max Act: 3.0543. Min Act: -0.1700

Data Index: 7919455 (The Pile)

Max Activating Token Index: 498

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.9436. Min Act: -0.1700

Data Index: 2941523 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.9436. Min Act: -0.1700

Data Index: 8909254 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.9436. Min Act: -0.1699

Data Index: 1311292 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.9119. Min Act: -0.1700

Data Index: 1778679 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8960. Min Act: -0.1700

Data Index: 10187321 (The Pile)

Max Activating Token Index: 923

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8960. Min Act: -0.1700

Data Index: 1857891 (The Pile)

Max Activating Token Index: 105

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8960. Min Act: -0.1700

Data Index: 533064 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8960. Min Act: -0.1700

Data Index: 2827977 (The Pile)

Max Activating Token Index: 396

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8802. Min Act: -0.1700

Data Index: 10434939 (The Pile)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8802. Min Act: -0.1699

Data Index: 5556411 (The Pile)

Max Activating Token Index: 78

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8802. Min Act: -0.1699

Data Index: 2639239 (The Pile)

Max Activating Token Index: 64

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 5512112 (The Pile)

Max Activating Token Index: 333

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 3221832 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 6520034 (The Pile)

Max Activating Token Index: 53

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 7264386 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 7542318 (The Pile)

Max Activating Token Index: 616

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 609626 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 2570489 (The Pile)

Max Activating Token Index: 526

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0543. Min Range: -3.0543

Max Act: 2.8643. Min Act: -0.1700

Data Index: 539534 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #19