< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 12 in Layer 22

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.9544. Min Act: -0.1700

Data Index: 6331722 (The Pile)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.9074. Min Act: -0.1700

Data Index: 6008819 (The Pile)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8918. Min Act: -0.1700

Data Index: 5307949 (The Pile)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8605. Min Act: -0.1700

Data Index: 8589627 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8605. Min Act: -0.1700

Data Index: 4988860 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8605. Min Act: -0.1700

Data Index: 9410815 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8449. Min Act: -0.1700

Data Index: 6287937 (The Pile)

Max Activating Token Index: 334

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8293. Min Act: -0.1700

Data Index: 1767663 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8136. Min Act: -0.1700

Data Index: 7643830 (The Pile)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8136. Min Act: -0.1700

Data Index: 4807772 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8136. Min Act: -0.1700

Data Index: 6049731 (The Pile)

Max Activating Token Index: 145

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.8136. Min Act: -0.1700

Data Index: 7711507 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7980. Min Act: -0.1700

Data Index: 2754027 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7980. Min Act: -0.1700

Data Index: 8949005 (The Pile)

Max Activating Token Index: 596

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7980. Min Act: -0.1700

Data Index: 2420917 (The Pile)

Max Activating Token Index: 103

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7980. Min Act: -0.1700

Data Index: 6817519 (The Pile)

Max Activating Token Index: 722

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7823. Min Act: -0.1700

Data Index: 8764017 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7823. Min Act: -0.1700

Data Index: 3394157 (The Pile)

Max Activating Token Index: 594

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7823. Min Act: -0.1700

Data Index: 5556169 (The Pile)

Max Activating Token Index: 155

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9544. Min Range: -3.9544

Max Act: 3.7823. Min Act: -0.1700

Data Index: 7828630 (The Pile)

Max Activating Token Index: 180

Click toggle to see full text

Truncated

Full Text #19