< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2003 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3955. Min Act: -0.1700

Data Index: 10322710 (The Pile)

Max Activating Token Index: 762

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3465. Min Act: -0.1700

Data Index: 7963199 (The Pile)

Max Activating Token Index: 913

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3465. Min Act: -0.1700

Data Index: 3259694 (The Pile)

Max Activating Token Index: 575

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3301. Min Act: -0.1700

Data Index: 4237900 (The Pile)

Max Activating Token Index: 364

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3301. Min Act: -0.1700

Data Index: 1865630 (The Pile)

Max Activating Token Index: 929

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3137. Min Act: -0.1700

Data Index: 2865909 (The Pile)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3137. Min Act: -0.1700

Data Index: 7836585 (The Pile)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2972. Min Act: -0.1700

Data Index: 9669713 (The Pile)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3137. Min Act: -0.1700

Data Index: 4712839 (The Pile)

Max Activating Token Index: 725

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2972. Min Act: -0.1700

Data Index: 2879161 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2972. Min Act: -0.1688

Data Index: 6186133 (The Pile)

Max Activating Token Index: 185

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2972. Min Act: -0.1700

Data Index: 4499827 (The Pile)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3137. Min Act: -0.1700

Data Index: 9028768 (The Pile)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3137. Min Act: -0.1700

Data Index: 8194490 (The Pile)

Max Activating Token Index: 265

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2808. Min Act: -0.1680

Data Index: 9883697 (The Pile)

Max Activating Token Index: 158

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.3137. Min Act: -0.1700

Data Index: 10158998 (The Pile)

Max Activating Token Index: 121

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2972. Min Act: -0.1700

Data Index: 733181 (The Pile)

Max Activating Token Index: 751

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2478. Min Act: -0.1700

Data Index: 5122403 (The Pile)

Max Activating Token Index: 653

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2972. Min Act: -0.1700

Data Index: 5235928 (The Pile)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3955. Min Range: -2.3955

Max Act: 2.2643. Min Act: -0.1700

Data Index: 2141237 (The Pile)

Max Activating Token Index: 814

Click toggle to see full text

Truncated

Full Text #19