< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4 in Layer 18

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.0496. Min Range: -4.0496

Max Act: 4.0496. Min Act: -0.1700

Data Index: 2528929 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.8933. Min Act: -0.1700

Data Index: 5787346 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.8620. Min Act: -0.1700

Data Index: 5316147 (The Pile)

Max Activating Token Index: 908

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.8307. Min Act: -0.1700

Data Index: 5459531 (The Pile)

Max Activating Token Index: 874

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.8151. Min Act: -0.1700

Data Index: 2002891 (The Pile)

Max Activating Token Index: 753

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.7682. Min Act: -0.1700

Data Index: 9004718 (The Pile)

Max Activating Token Index: 547

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.7369. Min Act: -0.1700

Data Index: 2243932 (The Pile)

Max Activating Token Index: 581

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.7369. Min Act: -0.1700

Data Index: 4025150 (The Pile)

Max Activating Token Index: 73

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.7369. Min Act: -0.1700

Data Index: 9788081 (The Pile)

Max Activating Token Index: 410

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.7369. Min Act: -0.1700

Data Index: 3401099 (The Pile)

Max Activating Token Index: 843

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.7056. Min Act: -0.1700

Data Index: 4742349 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6899. Min Act: -0.1700

Data Index: 8038533 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6899. Min Act: -0.1700

Data Index: 3632299 (The Pile)

Max Activating Token Index: 192

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6899. Min Act: -0.1700

Data Index: 2381127 (The Pile)

Max Activating Token Index: 852

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6743. Min Act: -0.1700

Data Index: 9129014 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6586. Min Act: -0.1700

Data Index: 7184073 (The Pile)

Max Activating Token Index: 182

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6430. Min Act: -0.1700

Data Index: 9213442 (The Pile)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6430. Min Act: -0.1700

Data Index: 9433086 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6273. Min Act: -0.1700

Data Index: 2706247 (The Pile)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0496. Min Range: -4.0496

Max Act: 3.6273. Min Act: -0.1700

Data Index: 3020063 (The Pile)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #19