< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 9 in Layer 14

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.6203. Min Act: -0.1700

Data Index: 1352129 (The Pile)

Max Activating Token Index: 809

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.6047. Min Act: -0.1700

Data Index: 6235217 (The Pile)

Max Activating Token Index: 657

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5890. Min Act: -0.1700

Data Index: 4579049 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5734. Min Act: -0.1700

Data Index: 5750389 (The Pile)

Max Activating Token Index: 389

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5577. Min Act: -0.1700

Data Index: 2745713 (The Pile)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5577. Min Act: -0.1700

Data Index: 4288233 (The Pile)

Max Activating Token Index: 593

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5577. Min Act: -0.1700

Data Index: 1648233 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5420. Min Act: -0.1700

Data Index: 6647702 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5264. Min Act: -0.1700

Data Index: 8187534 (The Pile)

Max Activating Token Index: 841

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.5107. Min Act: -0.1700

Data Index: 10207382 (The Pile)

Max Activating Token Index: 986

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4950. Min Act: -0.1700

Data Index: 3513081 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4794. Min Act: -0.1700

Data Index: 10225673 (The Pile)

Max Activating Token Index: 421

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4794. Min Act: -0.1700

Data Index: 3210083 (The Pile)

Max Activating Token Index: 392

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4637. Min Act: -0.1700

Data Index: 1518204 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4637. Min Act: -0.1700

Data Index: 6116007 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4637. Min Act: -0.1700

Data Index: 2435933 (The Pile)

Max Activating Token Index: 570

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4480. Min Act: -0.1700

Data Index: 5484426 (The Pile)

Max Activating Token Index: 891

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4480. Min Act: -0.1700

Data Index: 6053491 (The Pile)

Max Activating Token Index: 608

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4480. Min Act: -0.1700

Data Index: 5045390 (The Pile)

Max Activating Token Index: 976

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6203. Min Range: -3.6203

Max Act: 3.4480. Min Act: -0.1700

Data Index: 1158576 (The Pile)

Max Activating Token Index: 964

Click toggle to see full text

Truncated

Full Text #19