< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 40 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.2039. Min Range: -4.2039

Max Act: 4.2039. Min Act: -0.1700

Data Index: 7618748 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.2039. Min Range: -4.2039

Max Act: 4.1727. Min Act: -0.1700

Data Index: 10795100 (The Pile)

Max Activating Token Index: 122

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.6567. Min Act: -0.1700

Data Index: 8303694 (The Pile)

Max Activating Token Index: 950

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.6254. Min Act: -0.1700

Data Index: 519212 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.6254. Min Act: -0.1700

Data Index: 1979964 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.6097. Min Act: -0.1700

Data Index: 5880007 (The Pile)

Max Activating Token Index: 1013

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5940. Min Act: -0.1700

Data Index: 8646676 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5940. Min Act: -0.1700

Data Index: 3863237 (The Pile)

Max Activating Token Index: 413

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5784. Min Act: -0.1700

Data Index: 5214669 (The Pile)

Max Activating Token Index: 662

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5627. Min Act: -0.1700

Data Index: 3763360 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5471. Min Act: -0.1700

Data Index: 7574769 (The Pile)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5471. Min Act: -0.1700

Data Index: 6024634 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5471. Min Act: -0.1700

Data Index: 10546222 (The Pile)

Max Activating Token Index: 332

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5314. Min Act: -0.1700

Data Index: 1592383 (The Pile)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5314. Min Act: -0.1700

Data Index: 1748970 (The Pile)

Max Activating Token Index: 321

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5001. Min Act: -0.1700

Data Index: 9955444 (The Pile)

Max Activating Token Index: 825

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5001. Min Act: -0.1700

Data Index: 7344861 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.5001. Min Act: -0.1700

Data Index: 8289097 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.4687. Min Act: -0.1700

Data Index: 10065870 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.2039. Min Range: -4.2039

Max Act: 3.4687. Min Act: -0.1700

Data Index: 7421110 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #19