< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 3066 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3587. Min Act: -0.1700

Data Index: 2272397 (The Pile)

Max Activating Token Index: 289

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3259. Min Act: -0.1700

Data Index: 1543355 (The Pile)

Max Activating Token Index: 674

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3259. Min Act: -0.1700

Data Index: 5218398 (The Pile)

Max Activating Token Index: 900

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3259. Min Act: -0.1700

Data Index: 9073214 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 2082311 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 653075 (The Pile)

Max Activating Token Index: 539

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 2887681 (The Pile)

Max Activating Token Index: 560

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 9572393 (The Pile)

Max Activating Token Index: 810

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 7085293 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 6328090 (The Pile)

Max Activating Token Index: 459

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.3095. Min Act: -0.1700

Data Index: 6071664 (The Pile)

Max Activating Token Index: 408

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2930. Min Act: -0.1700

Data Index: 2309333 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2930. Min Act: -0.1700

Data Index: 7240631 (The Pile)

Max Activating Token Index: 328

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2930. Min Act: -0.1700

Data Index: 5783430 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2766. Min Act: -0.1700

Data Index: 8670166 (The Pile)

Max Activating Token Index: 970

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2766. Min Act: -0.1700

Data Index: 2881615 (The Pile)

Max Activating Token Index: 611

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2766. Min Act: -0.1700

Data Index: 1244170 (The Pile)

Max Activating Token Index: 735

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2766. Min Act: -0.1700

Data Index: 4541586 (The Pile)

Max Activating Token Index: 622

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2766. Min Act: -0.1700

Data Index: 7841061 (The Pile)

Max Activating Token Index: 742

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 2.3587. Min Range: -2.3587

Max Act: 2.2601. Min Act: -0.1700

Data Index: 4104631 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #19