< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 48 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-70m')



Text #0

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.9940. Min Act: -0.1700

Data Index: 905760 (The Pile)

Max Activating Token Index: 208

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.0878. Min Range: -4.0878

Max Act: 4.0878. Min Act: -0.1700

Data Index: 104951 (The Pile)

Max Activating Token Index: 669

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.9628. Min Act: -0.1700

Data Index: 8158610 (The Pile)

Max Activating Token Index: 259

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.0878. Min Range: -4.0878

Max Act: 4.0565. Min Act: -0.1700

Data Index: 9470928 (The Pile)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.8064. Min Act: -0.1700

Data Index: 3756736 (The Pile)

Max Activating Token Index: 983

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.9002. Min Act: -0.1700

Data Index: 7022433 (The Pile)

Max Activating Token Index: 750

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.6499. Min Act: -0.1700

Data Index: 9395676 (The Pile)

Max Activating Token Index: 419

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.6812. Min Act: -0.1700

Data Index: 4337602 (The Pile)

Max Activating Token Index: 171

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.7125. Min Act: -0.1700

Data Index: 8939706 (The Pile)

Max Activating Token Index: 52

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.8064. Min Act: -0.1700

Data Index: 1698623 (The Pile)

Max Activating Token Index: 1018

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.9002. Min Act: -0.1700

Data Index: 3318384 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.4933. Min Act: -0.1700

Data Index: 5364872 (The Pile)

Max Activating Token Index: 739

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.3993. Min Act: -0.1700

Data Index: 8637501 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.8377. Min Act: -0.1700

Data Index: 6248360 (The Pile)

Max Activating Token Index: 399

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.7751. Min Act: -0.1700

Data Index: 145458 (The Pile)

Max Activating Token Index: 267

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.7438. Min Act: -0.1700

Data Index: 7511587 (The Pile)

Max Activating Token Index: 475

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.7751. Min Act: -0.1700

Data Index: 1783433 (The Pile)

Max Activating Token Index: 386

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.5873. Min Act: -0.1700

Data Index: 6192155 (The Pile)

Max Activating Token Index: 290

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.7438. Min Act: -0.1700

Data Index: 1792872 (The Pile)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.0878. Min Range: -4.0878

Max Act: 3.7125. Min Act: -0.1700

Data Index: 4084864 (The Pile)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #19