< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 17 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1414. Min Range: -3.1414

Max Act: 3.1414. Min Act: -0.1700

Data Index: 10650632 (The Pile)

Max Activating Token Index: 325

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1414. Min Range: -3.1414

Max Act: 3.1414. Min Act: -0.1700

Data Index: 8642676 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1414. Min Range: -3.1414

Max Act: 3.0783. Min Act: -0.1700

Data Index: 7500002 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1414. Min Range: -3.1414

Max Act: 3.0626. Min Act: -0.1700

Data Index: 8364280 (The Pile)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1414. Min Range: -3.1414

Max Act: 3.0152. Min Act: -0.1700

Data Index: 6676277 (The Pile)

Max Activating Token Index: 978

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.9994. Min Act: -0.1700

Data Index: 930119 (The Pile)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.9994. Min Act: -0.1700

Data Index: 196632 (The Pile)

Max Activating Token Index: 888

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.9677. Min Act: -0.1700

Data Index: 82891 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.9361. Min Act: -0.1700

Data Index: 1554611 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8885. Min Act: -0.1700

Data Index: 8681271 (The Pile)

Max Activating Token Index: 902

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8726. Min Act: -0.1700

Data Index: 5530126 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8726. Min Act: -0.1700

Data Index: 10433585 (The Pile)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8726. Min Act: -0.1700

Data Index: 10219507 (The Pile)

Max Activating Token Index: 172

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8726. Min Act: -0.1700

Data Index: 10656540 (The Pile)

Max Activating Token Index: 257

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8409. Min Act: -0.1700

Data Index: 2100422 (The Pile)

Max Activating Token Index: 424

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8409. Min Act: -0.1700

Data Index: 6701080 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8250. Min Act: -0.1700

Data Index: 10780452 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8250. Min Act: -0.1700

Data Index: 5137095 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8090. Min Act: -0.1700

Data Index: 1081585 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1414. Min Range: -3.1414

Max Act: 2.8090. Min Act: -0.1700

Data Index: 5368260 (The Pile)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #19