< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4094 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.2363. Min Act: -0.1700

Data Index: 7822849 (The Pile)

Max Activating Token Index: 904

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1891. Min Act: -0.1700

Data Index: 1050543 (The Pile)

Max Activating Token Index: 209

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1733. Min Act: -0.1700

Data Index: 10548113 (The Pile)

Max Activating Token Index: 993

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1733. Min Act: -0.1700

Data Index: 5265120 (The Pile)

Max Activating Token Index: 156

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1576. Min Act: -0.1700

Data Index: 7620162 (The Pile)

Max Activating Token Index: 369

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1576. Min Act: -0.1700

Data Index: 8422449 (The Pile)

Max Activating Token Index: 473

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1418. Min Act: -0.1700

Data Index: 95534 (The Pile)

Max Activating Token Index: 805

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1261. Min Act: -0.1700

Data Index: 5127450 (The Pile)

Max Activating Token Index: 1006

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1261. Min Act: -0.1700

Data Index: 6000934 (The Pile)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1261. Min Act: -0.1700

Data Index: 2590930 (The Pile)

Max Activating Token Index: 132

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1103. Min Act: -0.1700

Data Index: 7817083 (The Pile)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1103. Min Act: -0.1700

Data Index: 6545205 (The Pile)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1103. Min Act: -0.1700

Data Index: 5293798 (The Pile)

Max Activating Token Index: 275

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1103. Min Act: -0.1700

Data Index: 4116129 (The Pile)

Max Activating Token Index: 533

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.1103. Min Act: -0.1700

Data Index: 8320178 (The Pile)

Max Activating Token Index: 117

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.0946. Min Act: -0.1700

Data Index: 2627532 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.0946. Min Act: -0.1700

Data Index: 2458423 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.0788. Min Act: -0.1700

Data Index: 3321800 (The Pile)

Max Activating Token Index: 915

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.0788. Min Act: -0.1700

Data Index: 4450413 (The Pile)

Max Activating Token Index: 946

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.2363. Min Range: -3.2363

Max Act: 3.0788. Min Act: -0.1700

Data Index: 3564976 (The Pile)

Max Activating Token Index: 619

Click toggle to see full text

Truncated

Full Text #19