< Prev | Home | Model | Random | Next >

Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer

Dataset: Open Web Text

Neuron 4042 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')



Text #0

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.8594. Min Act: -0.1700

Data Index: 7093101 (Open Web Text)

Max Activating Token Index: 55

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.8079. Min Act: -0.1700

Data Index: 8407887 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.8251. Min Act: -0.1700

Data Index: 4835906 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.8251. Min Act: -0.1700

Data Index: 5832927 (Open Web Text)

Max Activating Token Index: 72

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 3112698 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 351359 (Open Web Text)

Max Activating Token Index: 5

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 1878146 (Open Web Text)

Max Activating Token Index: 169

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.8079. Min Act: -0.1700

Data Index: 2490514 (Open Web Text)

Max Activating Token Index: 88

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 7103704 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5642931 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5629320 (Open Web Text)

Max Activating Token Index: 71

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5496110 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5359223 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 5119442 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 3152807 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 6768313 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 1857494 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 1831830 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 2589095 (Open Web Text)

Max Activating Token Index: 3

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.8594. Min Range: -1.8594

Max Act: 1.7907. Min Act: -0.1700

Data Index: 2830764 (Open Web Text)

Max Activating Token Index: 15

Click toggle to see full text

Truncated

Full Text #19