< Prev | Home | Model | Random | Next >

Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer

Dataset: Open Web Text

Neuron 5118 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.9998. Min Act: -0.1700

Data Index: 3802617 (Open Web Text)

Max Activating Token Index: 17

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.9150. Min Act: -0.1700

Data Index: 8415100 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.9150. Min Act: -0.1700

Data Index: 7095070 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.9150. Min Act: -0.1700

Data Index: 1824541 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.9150. Min Act: -0.1700

Data Index: 1477532 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8980. Min Act: -0.1700

Data Index: 7162322 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8980. Min Act: -0.1700

Data Index: 3176913 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8980. Min Act: -0.1700

Data Index: 2686278 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 7165238 (Open Web Text)

Max Activating Token Index: 10

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 6741980 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8809. Min Act: -0.1700

Data Index: 6089063 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8980. Min Act: -0.1700

Data Index: 5700566 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8809. Min Act: -0.1700

Data Index: 5549319 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8809. Min Act: -0.1700

Data Index: 2186544 (Open Web Text)

Max Activating Token Index: 12

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 6462184 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 3755222 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8467. Min Act: -0.1700

Data Index: 3386012 (Open Web Text)

Max Activating Token Index: 13

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 1783069 (Open Web Text)

Max Activating Token Index: 20

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 4943016 (Open Web Text)

Max Activating Token Index: 22

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9998. Min Range: -1.9998

Max Act: 1.8638. Min Act: -0.1700

Data Index: 3316833 (Open Web Text)

Max Activating Token Index: 8

Click toggle to see full text

Truncated

Full Text #19