< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 5086 in Layer 35

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.8090. Min Act: -0.1700

Data Index: 7632296 (Open Web Text)

Max Activating Token Index: 250

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.5902. Min Act: -0.1700

Data Index: 4954103 (Open Web Text)

Max Activating Token Index: 427

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.5590. Min Act: -0.1700

Data Index: 5811795 (Open Web Text)

Max Activating Token Index: 776

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.4340. Min Act: -0.1700

Data Index: 7618776 (Open Web Text)

Max Activating Token Index: 160

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.4027. Min Act: -0.1700

Data Index: 339379 (Open Web Text)

Max Activating Token Index: 620

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.3715. Min Act: -0.1700

Data Index: 744272 (Open Web Text)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.3402. Min Act: -0.1700

Data Index: 777697 (Open Web Text)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.2465. Min Act: -0.1700

Data Index: 3226457 (Open Web Text)

Max Activating Token Index: 268

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.2465. Min Act: -0.1700

Data Index: 1190343 (Open Web Text)

Max Activating Token Index: 83

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.2152. Min Act: -0.1700

Data Index: 1539236 (Open Web Text)

Max Activating Token Index: 518

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.1840. Min Act: -0.1700

Data Index: 3322080 (Open Web Text)

Max Activating Token Index: 205

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.1840. Min Act: -0.1700

Data Index: 8549173 (Open Web Text)

Max Activating Token Index: 318

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.2152. Min Act: -0.1700

Data Index: 2802975 (Open Web Text)

Max Activating Token Index: 955

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.1840. Min Act: -0.1700

Data Index: 262603 (Open Web Text)

Max Activating Token Index: 352

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.1215. Min Act: -0.1700

Data Index: 1822457 (Open Web Text)

Max Activating Token Index: 170

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 6.8090. Min Range: -6.8090

Max Act: 6.0277. Min Act: -0.1700

Data Index: 3904486 (Open Web Text)

Max Activating Token Index: 580

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 6.8090. Min Range: -6.8090

Max Act: 5.9965. Min Act: -0.1700

Data Index: 274874 (Open Web Text)

Max Activating Token Index: 40

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 6.8090. Min Range: -6.8090

Max Act: 5.9965. Min Act: -0.1700

Data Index: 8372811 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 6.8090. Min Range: -6.8090

Max Act: 5.9652. Min Act: -0.1700

Data Index: 8035363 (Open Web Text)

Max Activating Token Index: 561

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 6.8090. Min Range: -6.8090

Max Act: 5.9652. Min Act: -0.1700

Data Index: 7412028 (Open Web Text)

Max Activating Token Index: 19

Click toggle to see full text

Truncated

Full Text #19