< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 605 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: 5.0698. Min Range: -5.0698

Max Act: 5.0698. Min Act: -0.1700

Data Index: 338998 (The Pile)

Max Activating Token Index: 956

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.0698. Min Range: -5.0698

Max Act: 5.0386. Min Act: -0.1700

Data Index: 9802222 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.9448. Min Act: -0.1700

Data Index: 2027385 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8823. Min Act: -0.1700

Data Index: 4669880 (The Pile)

Max Activating Token Index: 703

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.9136. Min Act: -0.1700

Data Index: 8808701 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8511. Min Act: -0.1700

Data Index: 4060430 (The Pile)

Max Activating Token Index: 699

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8511. Min Act: -0.1700

Data Index: 5960069 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8511. Min Act: -0.1700

Data Index: 219193 (The Pile)

Max Activating Token Index: 501

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8511. Min Act: -0.1700

Data Index: 3625071 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.9136. Min Act: -0.1700

Data Index: 3529973 (The Pile)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.9136. Min Act: -0.1700

Data Index: 1130901 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8198. Min Act: -0.1700

Data Index: 1079773 (The Pile)

Max Activating Token Index: 860

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8823. Min Act: -0.1700

Data Index: 7232684 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.8511. Min Act: -0.1700

Data Index: 9993611 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.7886. Min Act: -0.1700

Data Index: 6195731 (The Pile)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.7573. Min Act: -0.1700

Data Index: 6858995 (The Pile)

Max Activating Token Index: 247

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.7886. Min Act: -0.1700

Data Index: 132556 (The Pile)

Max Activating Token Index: 516

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.7886. Min Act: -0.1700

Data Index: 9536067 (The Pile)

Max Activating Token Index: 279

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.7573. Min Act: -0.1700

Data Index: 4496205 (The Pile)

Max Activating Token Index: 242

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.0698. Min Range: -5.0698

Max Act: 4.7260. Min Act: -0.1700

Data Index: 3089284 (The Pile)

Max Activating Token Index: 690

Click toggle to see full text

Truncated

Full Text #19