< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4059 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.6518. Min Act: -0.1700

Data Index: 10313567 (The Pile)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.5735. Min Act: -0.1700

Data Index: 9039400 (The Pile)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.5735. Min Act: -0.1700

Data Index: 3031662 (The Pile)

Max Activating Token Index: 893

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.5578. Min Act: -0.1700

Data Index: 553507 (The Pile)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.5422. Min Act: -0.1700

Data Index: 4852814 (The Pile)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4952. Min Act: -0.1700

Data Index: 5297169 (The Pile)

Max Activating Token Index: 600

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4952. Min Act: -0.1700

Data Index: 7641454 (The Pile)

Max Activating Token Index: 486

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4795. Min Act: -0.1700

Data Index: 7754375 (The Pile)

Max Activating Token Index: 54

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4795. Min Act: -0.1700

Data Index: 1526769 (The Pile)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4638. Min Act: -0.1700

Data Index: 2741721 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4638. Min Act: -0.1700

Data Index: 7241930 (The Pile)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4638. Min Act: -0.1700

Data Index: 6894372 (The Pile)

Max Activating Token Index: 577

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4482. Min Act: -0.1700

Data Index: 3354948 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4482. Min Act: -0.1700

Data Index: 5753877 (The Pile)

Max Activating Token Index: 402

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4482. Min Act: -0.1700

Data Index: 5844480 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4482. Min Act: -0.1700

Data Index: 5894754 (The Pile)

Max Activating Token Index: 943

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4482. Min Act: -0.1700

Data Index: 5913291 (The Pile)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4482. Min Act: -0.1700

Data Index: 6211108 (The Pile)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4325. Min Act: -0.1700

Data Index: 1812175 (The Pile)

Max Activating Token Index: 793

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.6518. Min Range: -3.6518

Max Act: 3.4168. Min Act: -0.1700

Data Index: 6671312 (The Pile)

Max Activating Token Index: 476

Click toggle to see full text

Truncated

Full Text #19