< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 10 in Layer 8

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.5853. Min Act: -0.1700

Data Index: 3060362 (Open Web Text)

Max Activating Token Index: 661

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.4290. Min Act: -0.1700

Data Index: 3670415 (Open Web Text)

Max Activating Token Index: 971

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3978. Min Act: -0.1700

Data Index: 1419491 (Open Web Text)

Max Activating Token Index: 347

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3665. Min Act: -0.1700

Data Index: 6109911 (Open Web Text)

Max Activating Token Index: 196

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3665. Min Act: -0.1700

Data Index: 3907376 (Open Web Text)

Max Activating Token Index: 605

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3353. Min Act: -0.1700

Data Index: 8634460 (Open Web Text)

Max Activating Token Index: 959

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3353. Min Act: -0.1700

Data Index: 6316154 (Open Web Text)

Max Activating Token Index: 224

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3040. Min Act: -0.1700

Data Index: 1432420 (Open Web Text)

Max Activating Token Index: 651

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2728. Min Act: -0.1700

Data Index: 8209763 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2728. Min Act: -0.1700

Data Index: 5458525 (Open Web Text)

Max Activating Token Index: 301

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3040. Min Act: -0.1700

Data Index: 6739672 (Open Web Text)

Max Activating Token Index: 637

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2728. Min Act: -0.1700

Data Index: 6383261 (Open Web Text)

Max Activating Token Index: 312

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3353. Min Act: -0.1700

Data Index: 4075750 (Open Web Text)

Max Activating Token Index: 349

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3040. Min Act: -0.1700

Data Index: 1087673 (Open Web Text)

Max Activating Token Index: 29

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.3353. Min Act: -0.1700

Data Index: 963637 (Open Web Text)

Max Activating Token Index: 604

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2728. Min Act: -0.1700

Data Index: 1823783 (Open Web Text)

Max Activating Token Index: 60

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2415. Min Act: -0.1700

Data Index: 6617794 (Open Web Text)

Max Activating Token Index: 157

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2415. Min Act: -0.1700

Data Index: 5180925 (Open Web Text)

Max Activating Token Index: 752

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2728. Min Act: -0.1700

Data Index: 7398510 (Open Web Text)

Max Activating Token Index: 391

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 4.5853. Min Range: -4.5853

Max Act: 4.2728. Min Act: -0.1700

Data Index: 6080069 (Open Web Text)

Max Activating Token Index: 324

Click toggle to see full text

Truncated

Full Text #19