< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4093 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 1922953 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 5912924 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 109627 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 9034783 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 8002296 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 2560727 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 9374874 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 5819821 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 2487428 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 5129600 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 9302923 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 4526187 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 4400943 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 534182 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 3995842 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 2692044 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 7621218 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 6673324 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 6184434 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7107. Min Range: -3.7107

Max Act: 3.7107. Min Act: -0.1700

Data Index: 3560154 (The Pile)

Max Activating Token Index: 1

Click toggle to see full text

Truncated

Full Text #19