< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 2994 in Layer 9

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('pythia-160m')



Text #0

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.8999. Min Act: -0.1700

Data Index: 7783017 (The Pile)

Max Activating Token Index: 892

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.6183. Min Act: -0.1700

Data Index: 4020398 (The Pile)

Max Activating Token Index: 483

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.6183. Min Act: -0.1700

Data Index: 7676089 (The Pile)

Max Activating Token Index: 154

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.6183. Min Act: -0.1700

Data Index: 1952517 (The Pile)

Max Activating Token Index: 795

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.6027. Min Act: -0.1700

Data Index: 2581458 (The Pile)

Max Activating Token Index: 989

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.5870. Min Act: -0.1700

Data Index: 6183396 (The Pile)

Max Activating Token Index: 294

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.5400. Min Act: -0.1700

Data Index: 5789176 (The Pile)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.5244. Min Act: -0.1700

Data Index: 9265836 (The Pile)

Max Activating Token Index: 578

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.5087. Min Act: -0.1700

Data Index: 3562471 (The Pile)

Max Activating Token Index: 456

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4930. Min Act: -0.1700

Data Index: 6338208 (The Pile)

Max Activating Token Index: 463

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4930. Min Act: -0.1700

Data Index: 365385 (The Pile)

Max Activating Token Index: 817

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4774. Min Act: -0.1700

Data Index: 8392962 (The Pile)

Max Activating Token Index: 949

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4617. Min Act: -0.1700

Data Index: 9008710 (The Pile)

Max Activating Token Index: 262

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4617. Min Act: -0.1700

Data Index: 6633508 (The Pile)

Max Activating Token Index: 872

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4617. Min Act: -0.1700

Data Index: 5710131 (The Pile)

Max Activating Token Index: 865

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4617. Min Act: -0.1700

Data Index: 3619727 (The Pile)

Max Activating Token Index: 221

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4460. Min Act: -0.1700

Data Index: 2812943 (The Pile)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4460. Min Act: -0.1700

Data Index: 10125372 (The Pile)

Max Activating Token Index: 934

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4303. Min Act: -0.1700

Data Index: 1137546 (The Pile)

Max Activating Token Index: 861

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8999. Min Range: -3.8999

Max Act: 3.4303. Min Act: -0.1700

Data Index: 6864133 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #19