< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4021 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: 3.6812. Min Range: -3.6812

Max Act: 3.6812. Min Act: -0.1700

Data Index: 1020828 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6812. Min Act: -0.1700

Data Index: 5870560 (The Pile)

Max Activating Token Index: 1022

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6656. Min Act: -0.1700

Data Index: 1887718 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6499. Min Act: -0.1700

Data Index: 97165 (The Pile)

Max Activating Token Index: 559

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6499. Min Act: -0.1700

Data Index: 7378388 (The Pile)

Max Activating Token Index: 541

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6499. Min Act: -0.1700

Data Index: 4725019 (The Pile)

Max Activating Token Index: 919

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6499. Min Act: -0.1700

Data Index: 1511398 (The Pile)

Max Activating Token Index: 780

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6343. Min Act: -0.1700

Data Index: 5217261 (The Pile)

Max Activating Token Index: 355

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6343. Min Act: -0.1700

Data Index: 917034 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6186. Min Act: -0.1700

Data Index: 9728583 (The Pile)

Max Activating Token Index: 926

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6186. Min Act: -0.1700

Data Index: 516042 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6186. Min Act: -0.1700

Data Index: 330101 (The Pile)

Max Activating Token Index: 794

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6186. Min Act: -0.1700

Data Index: 3676913 (The Pile)

Max Activating Token Index: 716

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6186. Min Act: -0.1700

Data Index: 3078570 (The Pile)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6186. Min Act: -0.1700

Data Index: 10541433 (The Pile)

Max Activating Token Index: 792

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6030. Min Act: -0.1700

Data Index: 4731510 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6030. Min Act: -0.1700

Data Index: 236278 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6030. Min Act: -0.1700

Data Index: 395583 (The Pile)

Max Activating Token Index: 768

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6030. Min Act: -0.1700

Data Index: 7436262 (The Pile)

Max Activating Token Index: 718

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6812. Min Range: -3.6812

Max Act: 3.6030. Min Act: -0.1700

Data Index: 2819075 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #19