< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4058 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.2272. Min Range: -4.2272

Max Act: 4.2272. Min Act: -0.1700

Data Index: 7661848 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.2272. Min Range: -4.2272

Max Act: 4.0709. Min Act: -0.1700

Data Index: 683219 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.2272. Min Range: -4.2272

Max Act: 4.0397. Min Act: -0.1700

Data Index: 3534603 (The Pile)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.2272. Min Range: -4.2272

Max Act: 4.0084. Min Act: -0.1700

Data Index: 6544517 (The Pile)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.9771. Min Act: -0.1700

Data Index: 10601388 (The Pile)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.9302. Min Act: -0.1700

Data Index: 3424310 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.8677. Min Act: -0.1700

Data Index: 9974883 (The Pile)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.8364. Min Act: -0.1700

Data Index: 1334454 (The Pile)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.8364. Min Act: -0.1700

Data Index: 1596803 (The Pile)

Max Activating Token Index: 304

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.8364. Min Act: -0.1700

Data Index: 627960 (The Pile)

Max Activating Token Index: 538

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.8051. Min Act: -0.1700

Data Index: 3198220 (The Pile)

Max Activating Token Index: 411

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.8051. Min Act: -0.1700

Data Index: 4177550 (The Pile)

Max Activating Token Index: 276

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7895. Min Act: -0.1700

Data Index: 738254 (The Pile)

Max Activating Token Index: 178

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7895. Min Act: -0.1700

Data Index: 9127290 (The Pile)

Max Activating Token Index: 481

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7895. Min Act: -0.1700

Data Index: 2942291 (The Pile)

Max Activating Token Index: 183

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7739. Min Act: -0.1700

Data Index: 7844107 (The Pile)

Max Activating Token Index: 14

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7426. Min Act: -0.1700

Data Index: 4850318 (The Pile)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7426. Min Act: -0.1700

Data Index: 9892583 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7269. Min Act: -0.1700

Data Index: 4637615 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.2272. Min Range: -4.2272

Max Act: 3.7269. Min Act: -0.1700

Data Index: 5353846 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #19