< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 22 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.7501. Min Act: -0.1700

Data Index: 273326 (Open Web Text)

Max Activating Token Index: 108

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.7501. Min Act: -0.1700

Data Index: 5958135 (Open Web Text)

Max Activating Token Index: 494

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.6876. Min Act: -0.1700

Data Index: 7533889 (Open Web Text)

Max Activating Token Index: 390

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.6251. Min Act: -0.1700

Data Index: 4536832 (Open Web Text)

Max Activating Token Index: 7

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5938. Min Act: -0.1700

Data Index: 6355997 (Open Web Text)

Max Activating Token Index: 101

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5938. Min Act: -0.1700

Data Index: 4567097 (Open Web Text)

Max Activating Token Index: 738

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5938. Min Act: -0.1700

Data Index: 5857931 (Open Web Text)

Max Activating Token Index: 528

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5313. Min Act: -0.1700

Data Index: 2626047 (Open Web Text)

Max Activating Token Index: 370

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5626. Min Act: -0.1700

Data Index: 205482 (Open Web Text)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5313. Min Act: -0.1700

Data Index: 574950 (Open Web Text)

Max Activating Token Index: 936

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5000. Min Act: -0.1700

Data Index: 7539249 (Open Web Text)

Max Activating Token Index: 452

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4688. Min Act: -0.1700

Data Index: 7670905 (Open Web Text)

Max Activating Token Index: 137

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5000. Min Act: -0.1700

Data Index: 3660981 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4688. Min Act: -0.1700

Data Index: 7051159 (Open Web Text)

Max Activating Token Index: 11

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4375. Min Act: -0.1700

Data Index: 597004 (Open Web Text)

Max Activating Token Index: 188

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.5000. Min Act: -0.1700

Data Index: 7629648 (Open Web Text)

Max Activating Token Index: 721

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4063. Min Act: -0.1700

Data Index: 5504850 (Open Web Text)

Max Activating Token Index: 584

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4375. Min Act: -0.1700

Data Index: 6570868 (Open Web Text)

Max Activating Token Index: 38

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4375. Min Act: -0.1700

Data Index: 3482350 (Open Web Text)

Max Activating Token Index: 63

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.7501. Min Range: -4.7501

Max Act: 4.4688. Min Act: -0.1700

Data Index: 2036804 (Open Web Text)

Max Activating Token Index: 906

Click toggle to see full text

Truncated

Full Text #19