< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 4075 in Layer 5

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.1063. Min Act: -0.1700

Data Index: 4560740 (Open Web Text)

Max Activating Token Index: 537

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 5721554 (Open Web Text)

Max Activating Token Index: 918

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 1047320 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 5440258 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 2071773 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 8066351 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 6578236 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 4214008 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 3214494 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 7950813 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 5276113 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 8130285 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 5163549 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 7398052 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 5626649 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 385090 (Open Web Text)

Max Activating Token Index: 2

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0125. Min Act: -0.1700

Data Index: 5665757 (Open Web Text)

Max Activating Token Index: 227

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0125. Min Act: -0.1700

Data Index: 5520158 (Open Web Text)

Max Activating Token Index: 344

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.1063. Min Range: -4.1063

Max Act: 4.0438. Min Act: -0.1700

Data Index: 2143348 (Open Web Text)

Max Activating Token Index: 231

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.1063. Min Range: -4.1063

Max Act: 3.9812. Min Act: -0.1700

Data Index: 6121569 (Open Web Text)

Max Activating Token Index: 21

Click toggle to see full text

Truncated

Full Text #19