< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4078 in Layer 23

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.9116. Min Act: -0.1700

Data Index: 3813272 (The Pile)

Max Activating Token Index: 711

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.7708. Min Act: -0.1700

Data Index: 1762831 (The Pile)

Max Activating Token Index: 176

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.7083. Min Act: -0.1700

Data Index: 356537 (The Pile)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6926. Min Act: -0.1700

Data Index: 1184068 (The Pile)

Max Activating Token Index: 485

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6770. Min Act: -0.1700

Data Index: 1774727 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6613. Min Act: -0.1700

Data Index: 6887788 (The Pile)

Max Activating Token Index: 851

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6457. Min Act: -0.1700

Data Index: 4836921 (The Pile)

Max Activating Token Index: 572

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6300. Min Act: -0.1700

Data Index: 7655303 (The Pile)

Max Activating Token Index: 310

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6300. Min Act: -0.1700

Data Index: 9118044 (The Pile)

Max Activating Token Index: 186

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6143. Min Act: -0.1700

Data Index: 2439598 (The Pile)

Max Activating Token Index: 362

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.6143. Min Act: -0.1700

Data Index: 8661226 (The Pile)

Max Activating Token Index: 127

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5987. Min Act: -0.1700

Data Index: 4763202 (The Pile)

Max Activating Token Index: 924

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5830. Min Act: -0.1700

Data Index: 494576 (The Pile)

Max Activating Token Index: 691

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5674. Min Act: -0.1700

Data Index: 3071471 (The Pile)

Max Activating Token Index: 834

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5360. Min Act: -0.1700

Data Index: 4373499 (The Pile)

Max Activating Token Index: 98

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5360. Min Act: -0.1699

Data Index: 4377888 (The Pile)

Max Activating Token Index: 847

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5360. Min Act: -0.1700

Data Index: 5389236 (The Pile)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5360. Min Act: -0.1700

Data Index: 1789936 (The Pile)

Max Activating Token Index: 480

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5360. Min Act: -0.1700

Data Index: 363513 (The Pile)

Max Activating Token Index: 213

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.9116. Min Range: -3.9116

Max Act: 3.5204. Min Act: -0.1700

Data Index: 298764 (The Pile)

Max Activating Token Index: 787

Click toggle to see full text

Truncated

Full Text #19