< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4078 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.8029. Min Act: -0.1700

Data Index: 2383720 (The Pile)

Max Activating Token Index: 76

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.6464. Min Act: -0.1700

Data Index: 5441973 (The Pile)

Max Activating Token Index: 144

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.6307. Min Act: -0.1700

Data Index: 1657398 (The Pile)

Max Activating Token Index: 737

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.6307. Min Act: -0.1700

Data Index: 8087305 (The Pile)

Max Activating Token Index: 680

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5994. Min Act: -0.1700

Data Index: 5814344 (The Pile)

Max Activating Token Index: 766

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5524. Min Act: -0.1700

Data Index: 4855274 (The Pile)

Max Activating Token Index: 228

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5368. Min Act: -0.1700

Data Index: 9119447 (The Pile)

Max Activating Token Index: 671

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5368. Min Act: -0.1700

Data Index: 6926409 (The Pile)

Max Activating Token Index: 409

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5368. Min Act: -0.1700

Data Index: 1766055 (The Pile)

Max Activating Token Index: 808

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5368. Min Act: -0.1700

Data Index: 10318610 (The Pile)

Max Activating Token Index: 223

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5368. Min Act: -0.1700

Data Index: 5071761 (The Pile)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5055. Min Act: -0.1700

Data Index: 7816672 (The Pile)

Max Activating Token Index: 168

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5055. Min Act: -0.1700

Data Index: 2993436 (The Pile)

Max Activating Token Index: 937

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5055. Min Act: -0.1700

Data Index: 9351674 (The Pile)

Max Activating Token Index: 566

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.5055. Min Act: -0.1700

Data Index: 7021710 (The Pile)

Max Activating Token Index: 351

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.4898. Min Act: -0.1700

Data Index: 7862339 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.4898. Min Act: -0.1700

Data Index: 1416049 (The Pile)

Max Activating Token Index: 414

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.4898. Min Act: -0.1700

Data Index: 10599260 (The Pile)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.4741. Min Act: -0.1700

Data Index: 3282887 (The Pile)

Max Activating Token Index: 862

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8029. Min Range: -3.8029

Max Act: 3.4741. Min Act: -0.1700

Data Index: 4632918 (The Pile)

Max Activating Token Index: 992

Click toggle to see full text

Truncated

Full Text #19