< Prev | Home | Model | Random | Next >

Model: None

Dataset: The Pile

Neuron 4095 in Layer 12

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.1185. Min Act: -0.1700

Data Index: 9412163 (The Pile)

Max Activating Token Index: 707

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.1027. Min Act: -0.1700

Data Index: 7352903 (The Pile)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0870. Min Act: -0.1700

Data Index: 5436266 (The Pile)

Max Activating Token Index: 567

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0870. Min Act: -0.1700

Data Index: 9490702 (The Pile)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0712. Min Act: -0.1700

Data Index: 9641782 (The Pile)

Max Activating Token Index: 700

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0712. Min Act: -0.1700

Data Index: 4172461 (The Pile)

Max Activating Token Index: 153

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0238. Min Act: -0.1700

Data Index: 2192 (The Pile)

Max Activating Token Index: 790

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0080. Min Act: -0.1700

Data Index: 7860396 (The Pile)

Max Activating Token Index: 984

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0080. Min Act: -0.1700

Data Index: 6770307 (The Pile)

Max Activating Token Index: 299

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0080. Min Act: -0.1700

Data Index: 6505150 (The Pile)

Max Activating Token Index: 400

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.1185. Min Range: -3.1185

Max Act: 3.0080. Min Act: -0.1700

Data Index: 1164266 (The Pile)

Max Activating Token Index: 491

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9922. Min Act: -0.1700

Data Index: 7243641 (The Pile)

Max Activating Token Index: 985

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9922. Min Act: -0.1700

Data Index: 5542711 (The Pile)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9922. Min Act: -0.1700

Data Index: 10781735 (The Pile)

Max Activating Token Index: 346

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9922. Min Act: -0.1700

Data Index: 6794263 (The Pile)

Max Activating Token Index: 510

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9764. Min Act: -0.1700

Data Index: 1584079 (The Pile)

Max Activating Token Index: 938

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9764. Min Act: -0.1700

Data Index: 1050383 (The Pile)

Max Activating Token Index: 212

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9764. Min Act: -0.1700

Data Index: 2247967 (The Pile)

Max Activating Token Index: 599

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9764. Min Act: -0.1700

Data Index: 519693 (The Pile)

Max Activating Token Index: 449

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.1185. Min Range: -3.1185

Max Act: 2.9764. Min Act: -0.1700

Data Index: 9856682 (The Pile)

Max Activating Token Index: 850

Click toggle to see full text

Truncated

Full Text #19