< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 9 in Layer 10

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.3324. Min Act: -0.1700

Data Index: 5153623 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.0511. Min Act: -0.1700

Data Index: 4569188 (The Pile)

Max Activating Token Index: 425

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.3324. Min Range: -4.3324

Max Act: 4.0042. Min Act: -0.1699

Data Index: 7342817 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.9573. Min Act: -0.1700

Data Index: 112551 (The Pile)

Max Activating Token Index: 819

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.9417. Min Act: -0.1700

Data Index: 10216000 (The Pile)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.9104. Min Act: -0.1700

Data Index: 2568253 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.9104. Min Act: -0.1700

Data Index: 6926902 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8948. Min Act: -0.1699

Data Index: 10506965 (The Pile)

Max Activating Token Index: 140

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8948. Min Act: -0.1700

Data Index: 10699777 (The Pile)

Max Activating Token Index: 741

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8635. Min Act: -0.1700

Data Index: 1200163 (The Pile)

Max Activating Token Index: 925

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8635. Min Act: -0.1700

Data Index: 4169138 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8479. Min Act: -0.1700

Data Index: 9001411 (The Pile)

Max Activating Token Index: 56

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8322. Min Act: -0.1700

Data Index: 8528408 (The Pile)

Max Activating Token Index: 889

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8166. Min Act: -0.1700

Data Index: 4601025 (The Pile)

Max Activating Token Index: 291

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8166. Min Act: -0.1696

Data Index: 1885711 (The Pile)

Max Activating Token Index: 944

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8166. Min Act: -0.1700

Data Index: 7842417 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8166. Min Act: -0.1700

Data Index: 9164621 (The Pile)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8009. Min Act: -0.1700

Data Index: 9692538 (The Pile)

Max Activating Token Index: 373

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8009. Min Act: -0.1700

Data Index: 3194830 (The Pile)

Max Activating Token Index: 365

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.3324. Min Range: -4.3324

Max Act: 3.8009. Min Act: -0.1700

Data Index: 9831359 (The Pile)

Max Activating Token Index: 543

Click toggle to see full text

Truncated

Full Text #19