< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4037 in Layer 16

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7393. Min Act: -0.1700

Data Index: 4837349 (The Pile)

Max Activating Token Index: 397

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7237. Min Act: -0.1700

Data Index: 8748933 (The Pile)

Max Activating Token Index: 57

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.7080. Min Act: -0.1700

Data Index: 2072762 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6924. Min Act: -0.1700

Data Index: 8077674 (The Pile)

Max Activating Token Index: 319

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6924. Min Act: -0.1700

Data Index: 9368688 (The Pile)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6924. Min Act: -0.1700

Data Index: 6004918 (The Pile)

Max Activating Token Index: 6

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6767. Min Act: -0.1700

Data Index: 7276238 (The Pile)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6611. Min Act: -0.1700

Data Index: 9688329 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6454. Min Act: -0.1700

Data Index: 10454666 (The Pile)

Max Activating Token Index: 836

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6298. Min Act: -0.1700

Data Index: 1178744 (The Pile)

Max Activating Token Index: 255

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6298. Min Act: -0.1700

Data Index: 2512804 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6298. Min Act: -0.1700

Data Index: 9309310 (The Pile)

Max Activating Token Index: 203

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6141. Min Act: -0.1700

Data Index: 1095480 (The Pile)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.6141. Min Act: -0.1700

Data Index: 1068754 (The Pile)

Max Activating Token Index: 982

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5985. Min Act: -0.1700

Data Index: 6749057 (The Pile)

Max Activating Token Index: 433

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5985. Min Act: -0.1700

Data Index: 3668027 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5985. Min Act: -0.1700

Data Index: 8760519 (The Pile)

Max Activating Token Index: 542

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5985. Min Act: -0.1700

Data Index: 8201168 (The Pile)

Max Activating Token Index: 217

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5985. Min Act: -0.1700

Data Index: 8864002 (The Pile)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.7393. Min Range: -3.7393

Max Act: 3.5828. Min Act: -0.1700

Data Index: 1259398 (The Pile)

Max Activating Token Index: 454

Click toggle to see full text

Truncated

Full Text #19