< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4068 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.4748. Min Act: -0.1700

Data Index: 5951345 (The Pile)

Max Activating Token Index: 376

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.3186. Min Act: -0.1700

Data Index: 1279461 (The Pile)

Max Activating Token Index: 80

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.2873. Min Act: -0.1700

Data Index: 7439013 (The Pile)

Max Activating Token Index: 941

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.2561. Min Act: -0.1700

Data Index: 6490678 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.2248. Min Act: -0.1700

Data Index: 10145273 (The Pile)

Max Activating Token Index: 940

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.1310. Min Act: -0.1699

Data Index: 7681652 (The Pile)

Max Activating Token Index: 202

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.1310. Min Act: -0.1699

Data Index: 398553 (The Pile)

Max Activating Token Index: 962

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.1310. Min Act: -0.1700

Data Index: 1103952 (The Pile)

Max Activating Token Index: 100

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.1310. Min Act: -0.1700

Data Index: 2055277 (The Pile)

Max Activating Token Index: 726

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.0685. Min Act: -0.1699

Data Index: 3517052 (The Pile)

Max Activating Token Index: 736

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.0685. Min Act: -0.1700

Data Index: 3603050 (The Pile)

Max Activating Token Index: 129

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.0372. Min Act: -0.1700

Data Index: 5604467 (The Pile)

Max Activating Token Index: 897

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.0060. Min Act: -0.1700

Data Index: 871018 (The Pile)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.0060. Min Act: -0.1700

Data Index: 6157325 (The Pile)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.4748. Min Range: -4.4748

Max Act: 4.0060. Min Act: -0.1700

Data Index: 7932433 (The Pile)

Max Activating Token Index: 148

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.9903. Min Act: -0.1700

Data Index: 4514670 (The Pile)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.9903. Min Act: -0.1700

Data Index: 8634990 (The Pile)

Max Activating Token Index: 712

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.9903. Min Act: -0.1700

Data Index: 9522009 (The Pile)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.9903. Min Act: -0.1700

Data Index: 8871013 (The Pile)

Max Activating Token Index: 472

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.4748. Min Range: -4.4748

Max Act: 3.9903. Min Act: -0.1700

Data Index: 7351400 (The Pile)

Max Activating Token Index: 965

Click toggle to see full text

Truncated

Full Text #19