< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 4079 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: 1.9068. Min Range: -1.9068

Max Act: 1.8898. Min Act: -0.1700

Data Index: 7093589 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.9068. Min Act: -0.1700

Data Index: 4156118 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8727. Min Act: -0.1700

Data Index: 8354449 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8727. Min Act: -0.1700

Data Index: 6661955 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8556. Min Act: -0.1700

Data Index: 1953652 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8556. Min Act: -0.1700

Data Index: 7095037 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8213. Min Act: -0.1700

Data Index: 1869904 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8213. Min Act: -0.1700

Data Index: 7571985 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8213. Min Act: -0.1700

Data Index: 774024 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8213. Min Act: -0.1700

Data Index: 5275478 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8213. Min Act: -0.1700

Data Index: 8777953 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8213. Min Act: -0.1700

Data Index: 6032102 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8041. Min Act: -0.1700

Data Index: 5036765 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8041. Min Act: -0.1700

Data Index: 3121743 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8041. Min Act: -0.1700

Data Index: 4539531 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8041. Min Act: -0.1700

Data Index: 260887 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.8041. Min Act: -0.1700

Data Index: 4455628 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.7869. Min Act: -0.1700

Data Index: 643987 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.7869. Min Act: -0.1700

Data Index: 1389748 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 1.9068. Min Range: -1.9068

Max Act: 1.7696. Min Act: -0.1700

Data Index: 706616 (Open Web Text)

Max Activating Token Index: 1023

Click toggle to see full text

Truncated

Full Text #19