< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 32 in Layer 2

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.0067. Min Range: -3.0067

Max Act: 3.0067. Min Act: -0.1700

Data Index: 9118574 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9909. Min Act: -0.1700

Data Index: 8152231 (The Pile)

Max Activating Token Index: 782

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9909. Min Act: -0.1700

Data Index: 8750968 (The Pile)

Max Activating Token Index: 823

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9750. Min Act: -0.1700

Data Index: 3937317 (The Pile)

Max Activating Token Index: 96

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9750. Min Act: -0.1700

Data Index: 6214077 (The Pile)

Max Activating Token Index: 434

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9592. Min Act: -0.1700

Data Index: 3419615 (The Pile)

Max Activating Token Index: 857

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9592. Min Act: -0.1700

Data Index: 6682094 (The Pile)

Max Activating Token Index: 251

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9592. Min Act: -0.1700

Data Index: 2697222 (The Pile)

Max Activating Token Index: 811

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9434. Min Act: -0.1700

Data Index: 9690299 (The Pile)

Max Activating Token Index: 757

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9434. Min Act: -0.1700

Data Index: 3150024 (The Pile)

Max Activating Token Index: 215

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9275. Min Act: -0.1700

Data Index: 7417678 (The Pile)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9275. Min Act: -0.1700

Data Index: 4293942 (The Pile)

Max Activating Token Index: 65

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9275. Min Act: -0.1700

Data Index: 7246129 (The Pile)

Max Activating Token Index: 557

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9275. Min Act: -0.1700

Data Index: 3369769 (The Pile)

Max Activating Token Index: 961

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.9117. Min Act: -0.1700

Data Index: 10587288 (The Pile)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8958. Min Act: -0.1700

Data Index: 4997642 (The Pile)

Max Activating Token Index: 235

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8958. Min Act: -0.1700

Data Index: 5096674 (The Pile)

Max Activating Token Index: 1002

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8958. Min Act: -0.1700

Data Index: 6818588 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8958. Min Act: -0.1700

Data Index: 8075847 (The Pile)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.0067. Min Range: -3.0067

Max Act: 2.8958. Min Act: -0.1700

Data Index: 7185089 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #19