< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1983 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.2476. Min Act: -0.1700

Data Index: 1495077 (The Pile)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.2161. Min Act: -0.1700

Data Index: 8305222 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.2004. Min Act: -0.1700

Data Index: 5151737 (The Pile)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1532. Min Act: -0.1700

Data Index: 6858166 (The Pile)

Max Activating Token Index: 407

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1532. Min Act: -0.1700

Data Index: 2623035 (The Pile)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1532. Min Act: -0.1700

Data Index: 4798488 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1374. Min Act: -0.1700

Data Index: 7621543 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1374. Min Act: -0.1700

Data Index: 4233224 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1374. Min Act: -0.1700

Data Index: 8573802 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1374. Min Act: -0.1700

Data Index: 4065462 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1217. Min Act: -0.1700

Data Index: 7230748 (The Pile)

Max Activating Token Index: 342

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1374. Min Act: -0.1700

Data Index: 7874136 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1217. Min Act: -0.1699

Data Index: 3160724 (The Pile)

Max Activating Token Index: 305

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1059. Min Act: -0.1700

Data Index: 2644831 (The Pile)

Max Activating Token Index: 552

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1059. Min Act: -0.1700

Data Index: 4836807 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1059. Min Act: -0.1700

Data Index: 6184411 (The Pile)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.1059. Min Act: -0.1700

Data Index: 4512701 (The Pile)

Max Activating Token Index: 86

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.0902. Min Act: -0.1700

Data Index: 9131732 (The Pile)

Max Activating Token Index: 701

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.0744. Min Act: -0.1700

Data Index: 7847555 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2476. Min Range: -3.2476

Max Act: 3.0744. Min Act: -0.1700

Data Index: 5167876 (The Pile)

Max Activating Token Index: 75

Click toggle to see full text

Truncated

Full Text #19