< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4034 in Layer 15

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.9153. Min Act: -0.1700

Data Index: 4375619 (The Pile)

Max Activating Token Index: 309

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.8684. Min Act: -0.1700

Data Index: 6256146 (The Pile)

Max Activating Token Index: 271

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.8528. Min Act: -0.1700

Data Index: 2070907 (The Pile)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.7746. Min Act: -0.1700

Data Index: 6932572 (The Pile)

Max Activating Token Index: 120

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.7433. Min Act: -0.1700

Data Index: 7351954 (The Pile)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.7120. Min Act: -0.1700

Data Index: 6212634 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.7120. Min Act: -0.1700

Data Index: 526362 (The Pile)

Max Activating Token Index: 27

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.7120. Min Act: -0.1700

Data Index: 9568637 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6963. Min Act: -0.1700

Data Index: 7433916 (The Pile)

Max Activating Token Index: 630

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6807. Min Act: -0.1700

Data Index: 111173 (The Pile)

Max Activating Token Index: 832

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6807. Min Act: -0.1700

Data Index: 7957201 (The Pile)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6494. Min Act: -0.1700

Data Index: 1364724 (The Pile)

Max Activating Token Index: 455

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6494. Min Act: -0.1700

Data Index: 6714401 (The Pile)

Max Activating Token Index: 672

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6494. Min Act: -0.1700

Data Index: 9801194 (The Pile)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6494. Min Act: -0.1700

Data Index: 481799 (The Pile)

Max Activating Token Index: 796

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6337. Min Act: -0.1700

Data Index: 4605000 (The Pile)

Max Activating Token Index: 479

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6181. Min Act: -0.1700

Data Index: 1785369 (The Pile)

Max Activating Token Index: 909

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6181. Min Act: -0.1700

Data Index: 2155869 (The Pile)

Max Activating Token Index: 833

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6024. Min Act: -0.1700

Data Index: 7948003 (The Pile)

Max Activating Token Index: 345

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9153. Min Range: -3.9153

Max Act: 3.6024. Min Act: -0.1700

Data Index: 3094963 (The Pile)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #19