< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2007 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.2673. Min Act: -0.1700

Data Index: 5785759 (The Pile)

Max Activating Token Index: 720

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.2359. Min Act: -0.1700

Data Index: 1243011 (The Pile)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.2201. Min Act: -0.1700

Data Index: 6599361 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1729. Min Act: -0.1700

Data Index: 3745257 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1729. Min Act: -0.1700

Data Index: 8442213 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1572. Min Act: -0.1700

Data Index: 3413296 (The Pile)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1414. Min Act: -0.1700

Data Index: 9782542 (The Pile)

Max Activating Token Index: 998

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1414. Min Act: -0.1700

Data Index: 9871764 (The Pile)

Max Activating Token Index: 988

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1414. Min Act: -0.1700

Data Index: 4211440 (The Pile)

Max Activating Token Index: 470

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1414. Min Act: -0.1700

Data Index: 4517380 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1414. Min Act: -0.1700

Data Index: 4029475 (The Pile)

Max Activating Token Index: 957

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1099. Min Act: -0.1700

Data Index: 6267723 (The Pile)

Max Activating Token Index: 274

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1099. Min Act: -0.1700

Data Index: 2608866 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.0942. Min Act: -0.1700

Data Index: 3615117 (The Pile)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.0942. Min Act: -0.1700

Data Index: 165670 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.0942. Min Act: -0.1700

Data Index: 5533520 (The Pile)

Max Activating Token Index: 927

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1099. Min Act: -0.1700

Data Index: 6262413 (The Pile)

Max Activating Token Index: 193

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1099. Min Act: -0.1700

Data Index: 6983452 (The Pile)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.1099. Min Act: -0.1700

Data Index: 2990030 (The Pile)

Max Activating Token Index: 201

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2673. Min Range: -3.2673

Max Act: 3.0468. Min Act: -0.1700

Data Index: 7203480 (The Pile)

Max Activating Token Index: 587

Click toggle to see full text

Truncated

Full Text #19