< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 3044 in Layer 7

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.8623. Min Act: -0.1700

Data Index: 8506057 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.6545. Min Act: -0.1700

Data Index: 2961109 (Open Web Text)

Max Activating Token Index: 684

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.5865. Min Act: -0.1700

Data Index: 3452099 (Open Web Text)

Max Activating Token Index: 969

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.5201. Min Act: -0.1700

Data Index: 3970287 (Open Web Text)

Max Activating Token Index: 317

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.5059. Min Act: -0.1700

Data Index: 3608430 (Open Web Text)

Max Activating Token Index: 678

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.5313. Min Act: -0.1700

Data Index: 8107920 (Open Web Text)

Max Activating Token Index: 878

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.5035. Min Act: -0.1700

Data Index: 4155436 (Open Web Text)

Max Activating Token Index: 1003

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.5134. Min Act: -0.1700

Data Index: 2506212 (Open Web Text)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4913. Min Act: -0.1700

Data Index: 7647809 (Open Web Text)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4745. Min Act: -0.1700

Data Index: 5139785 (Open Web Text)

Max Activating Token Index: 1016

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4778. Min Act: -0.1700

Data Index: 3165182 (Open Web Text)

Max Activating Token Index: 307

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4716. Min Act: -0.1700

Data Index: 1094614 (Open Web Text)

Max Activating Token Index: 954

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4636. Min Act: -0.1700

Data Index: 829720 (Open Web Text)

Max Activating Token Index: 777

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4674. Min Act: -0.1700

Data Index: 1793154 (Open Web Text)

Max Activating Token Index: 687

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4680. Min Act: -0.1700

Data Index: 8405054 (Open Web Text)

Max Activating Token Index: 931

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4558. Min Act: -0.1700

Data Index: 5101617 (Open Web Text)

Max Activating Token Index: 761

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4509. Min Act: -0.1700

Data Index: 268040 (Open Web Text)

Max Activating Token Index: 258

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4193. Min Act: -0.1700

Data Index: 2140281 (Open Web Text)

Max Activating Token Index: 1005

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4427. Min Act: -0.1700

Data Index: 7040695 (Open Web Text)

Max Activating Token Index: 727

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 3.8623. Min Range: -3.8623

Max Act: 3.4366. Min Act: -0.1700

Data Index: 4659065 (Open Web Text)

Max Activating Token Index: 1017

Click toggle to see full text

Truncated

Full Text #19