< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2045 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: 4.3230. Min Range: -4.3230

Max Act: 4.1667. Min Act: -0.1700

Data Index: 10666430 (The Pile)

Max Activating Token Index: 348

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0104. Min Act: -0.1700

Data Index: 6953347 (The Pile)

Max Activating Token Index: 868

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.1355. Min Act: -0.1700

Data Index: 3018774 (The Pile)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3230. Min Range: -4.3230

Max Act: 3.8541. Min Act: -0.1700

Data Index: 9909273 (The Pile)

Max Activating Token Index: 423

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0417. Min Act: -0.1699

Data Index: 6557714 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0417. Min Act: -0.1699

Data Index: 6813444 (The Pile)

Max Activating Token Index: 682

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0730. Min Act: -0.1700

Data Index: 735142 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.1042. Min Act: -0.1700

Data Index: 8992947 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.1667. Min Act: -0.1700

Data Index: 2432142 (The Pile)

Max Activating Token Index: 544

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0104. Min Act: -0.1700

Data Index: 10630773 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3230. Min Range: -4.3230

Max Act: 3.9792. Min Act: -0.1700

Data Index: 10491919 (The Pile)

Max Activating Token Index: 771

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.3230. Min Act: -0.1700

Data Index: 4941850 (The Pile)

Max Activating Token Index: 204

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0417. Min Act: -0.1700

Data Index: 4550656 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3230. Min Range: -4.3230

Max Act: 3.9166. Min Act: -0.1699

Data Index: 2669134 (The Pile)

Max Activating Token Index: 650

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0104. Min Act: -0.1699

Data Index: 8728212 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3230. Min Range: -4.3230

Max Act: 3.9166. Min Act: -0.1700

Data Index: 2378725 (The Pile)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.1042. Min Act: -0.1700

Data Index: 8146478 (The Pile)

Max Activating Token Index: 150

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0417. Min Act: -0.1700

Data Index: 3502634 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3230. Min Range: -4.3230

Max Act: 3.9166. Min Act: -0.1700

Data Index: 3432191 (The Pile)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3230. Min Range: -4.3230

Max Act: 4.0730. Min Act: -0.1700

Data Index: 625435 (The Pile)

Max Activating Token Index: 314

Click toggle to see full text

Truncated

Full Text #19