< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3008 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 12.1163. Min Range: -12.1163

Max Act: 12.1163. Min Act: -0.1700

Data Index: 4950650 (The Pile)

Max Activating Token Index: 649

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.9913. Min Act: -0.1700

Data Index: 5220315 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.9288. Min Act: -0.1700

Data Index: 7719709 (The Pile)

Max Activating Token Index: 666

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.6163. Min Act: -0.1700

Data Index: 6554732 (The Pile)

Max Activating Token Index: 844

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.3038. Min Act: -0.1700

Data Index: 792092 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.3038. Min Act: -0.1700

Data Index: 1858648 (The Pile)

Max Activating Token Index: 523

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.1788. Min Act: -0.1700

Data Index: 1514575 (The Pile)

Max Activating Token Index: 602

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 12.1163. Min Range: -12.1163

Max Act: 11.1788. Min Act: -0.1700

Data Index: 6178450 (The Pile)

Max Activating Token Index: 520

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.9288. Min Act: -0.1700

Data Index: 4865738 (The Pile)

Max Activating Token Index: 848

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.8663. Min Act: -0.1700

Data Index: 1761204 (The Pile)

Max Activating Token Index: 222

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.8038. Min Act: -0.1700

Data Index: 4342018 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.8038. Min Act: -0.1700

Data Index: 2350735 (The Pile)

Max Activating Token Index: 871

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.7413. Min Act: -0.1700

Data Index: 7590810 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.7413. Min Act: -0.1700

Data Index: 6433893 (The Pile)

Max Activating Token Index: 849

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.6788. Min Act: -0.1700

Data Index: 5642131 (The Pile)

Max Activating Token Index: 830

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.6788. Min Act: -0.1700

Data Index: 10286583 (The Pile)

Max Activating Token Index: 668

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.6163. Min Act: -0.1700

Data Index: 2017347 (The Pile)

Max Activating Token Index: 384

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.6163. Min Act: -0.1700

Data Index: 9253445 (The Pile)

Max Activating Token Index: 638

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.6163. Min Act: -0.1700

Data Index: 1988574 (The Pile)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 12.1163. Min Range: -12.1163

Max Act: 10.5538. Min Act: -0.1700

Data Index: 6952548 (The Pile)

Max Activating Token Index: 284

Click toggle to see full text

Truncated

Full Text #19