< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 20 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: 4.0422. Min Range: -4.0422

Max Act: 4.0422. Min Act: -0.1700

Data Index: 9904509 (The Pile)

Max Activating Token Index: 772

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.9484. Min Act: -0.1700

Data Index: 2356488 (The Pile)

Max Activating Token Index: 530

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.9484. Min Act: -0.1700

Data Index: 5552503 (The Pile)

Max Activating Token Index: 368

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.9171. Min Act: -0.1700

Data Index: 3640988 (The Pile)

Max Activating Token Index: 647

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8858. Min Act: -0.1700

Data Index: 4746787 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8858. Min Act: -0.1700

Data Index: 463460 (The Pile)

Max Activating Token Index: 363

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8858. Min Act: -0.1700

Data Index: 9485417 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8546. Min Act: -0.1700

Data Index: 1031317 (The Pile)

Max Activating Token Index: 298

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8546. Min Act: -0.1700

Data Index: 5613276 (The Pile)

Max Activating Token Index: 997

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8546. Min Act: -0.1700

Data Index: 8000121 (The Pile)

Max Activating Token Index: 755

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8546. Min Act: -0.1700

Data Index: 9023289 (The Pile)

Max Activating Token Index: 337

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8546. Min Act: -0.1700

Data Index: 9133160 (The Pile)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 9653816 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 6686073 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 3208086 (The Pile)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 8727754 (The Pile)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 5716733 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 1508114 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 8154048 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0422. Min Range: -4.0422

Max Act: 3.8233. Min Act: -0.1700

Data Index: 490659 (The Pile)

Max Activating Token Index: 440

Click toggle to see full text

Truncated

Full Text #19