< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 1990 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.0894. Min Act: -0.1700

Data Index: 9060982 (The Pile)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.1519. Min Act: -0.1700

Data Index: 10457883 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.0269. Min Act: -0.1700

Data Index: 10615261 (The Pile)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.2144. Min Act: -0.1700

Data Index: 3501145 (The Pile)

Max Activating Token Index: 478

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.7769. Min Act: -0.1700

Data Index: 9272626 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.9332. Min Act: -0.1700

Data Index: 9691675 (The Pile)

Max Activating Token Index: 642

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.8394. Min Act: -0.1700

Data Index: 5788431 (The Pile)

Max Activating Token Index: 415

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.0582. Min Act: -0.1700

Data Index: 7959719 (The Pile)

Max Activating Token Index: 33

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.1832. Min Act: -0.1700

Data Index: 704265 (The Pile)

Max Activating Token Index: 525

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.5894. Min Act: -0.1700

Data Index: 5188189 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.0582. Min Act: -0.1700

Data Index: 10166152 (The Pile)

Max Activating Token Index: 110

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.9019. Min Act: -0.1700

Data Index: 5694609 (The Pile)

Max Activating Token Index: 194

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.0269. Min Act: -0.1700

Data Index: 10063772 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.9957. Min Act: -0.1700

Data Index: 392246 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.9019. Min Act: -0.1700

Data Index: 3087043 (The Pile)

Max Activating Token Index: 49

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.2144. Min Range: -5.2144

Max Act: 5.1519. Min Act: -0.1700

Data Index: 10743288 (The Pile)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.9644. Min Act: -0.1700

Data Index: 5149953 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.7144. Min Act: -0.1700

Data Index: 5038520 (The Pile)

Max Activating Token Index: 136

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.8394. Min Act: -0.1700

Data Index: 2635064 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.2144. Min Range: -5.2144

Max Act: 4.9019. Min Act: -0.1700

Data Index: 840478 (The Pile)

Max Activating Token Index: 239

Click toggle to see full text

Truncated

Full Text #19