< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 4042 in Layer 12

Load this data into an Interactive Neuroscope

See Documentation here

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



Text #0

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.5016. Min Act: -0.1700

Data Index: 3567356 (Open Web Text)

Max Activating Token Index: 774

Click toggle to see full text

Truncated

Full Text #0


Text #1

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.4704. Min Act: -0.1700

Data Index: 3711769 (Open Web Text)

Max Activating Token Index: 448

Click toggle to see full text

Truncated

Full Text #1


Text #2

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.3766. Min Act: -0.1700

Data Index: 2150710 (Open Web Text)

Max Activating Token Index: 798

Click toggle to see full text

Truncated

Full Text #2


Text #3

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.3454. Min Act: -0.1700

Data Index: 2903716 (Open Web Text)

Max Activating Token Index: 504

Click toggle to see full text

Truncated

Full Text #3


Text #4

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.3141. Min Act: -0.1700

Data Index: 6589895 (Open Web Text)

Max Activating Token Index: 492

Click toggle to see full text

Truncated

Full Text #4


Text #5

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2829. Min Act: -0.1700

Data Index: 1366307 (Open Web Text)

Max Activating Token Index: 591

Click toggle to see full text

Truncated

Full Text #5


Text #6

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.3141. Min Act: -0.1700

Data Index: 646951 (Open Web Text)

Max Activating Token Index: 503

Click toggle to see full text

Truncated

Full Text #6


Text #7

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2204. Min Act: -0.1700

Data Index: 3952804 (Open Web Text)

Max Activating Token Index: 428

Click toggle to see full text

Truncated

Full Text #7


Text #8

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.3141. Min Act: -0.1700

Data Index: 8004345 (Open Web Text)

Max Activating Token Index: 821

Click toggle to see full text

Truncated

Full Text #8


Text #9

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2829. Min Act: -0.1700

Data Index: 5835142 (Open Web Text)

Max Activating Token Index: 381

Click toggle to see full text

Truncated

Full Text #9


Text #10

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.3141. Min Act: -0.1700

Data Index: 1428087 (Open Web Text)

Max Activating Token Index: 685

Click toggle to see full text

Truncated

Full Text #10


Text #11

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2516. Min Act: -0.1700

Data Index: 2008118 (Open Web Text)

Max Activating Token Index: 93

Click toggle to see full text

Truncated

Full Text #11


Text #12

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2829. Min Act: -0.1700

Data Index: 7804249 (Open Web Text)

Max Activating Token Index: 416

Click toggle to see full text

Truncated

Full Text #12


Text #13

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2204. Min Act: -0.1700

Data Index: 8228043 (Open Web Text)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #13


Text #14

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2204. Min Act: -0.1700

Data Index: 1189947 (Open Web Text)

Max Activating Token Index: 281

Click toggle to see full text

Truncated

Full Text #14


Text #15

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2516. Min Act: -0.1700

Data Index: 8500053 (Open Web Text)

Max Activating Token Index: 1019

Click toggle to see full text

Truncated

Full Text #15


Text #16

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2204. Min Act: -0.1700

Data Index: 5107022 (Open Web Text)

Max Activating Token Index: 598

Click toggle to see full text

Truncated

Full Text #16


Text #17

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.2204. Min Act: -0.1700

Data Index: 7079641 (Open Web Text)

Max Activating Token Index: 885

Click toggle to see full text

Truncated

Full Text #17


Text #18

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.1891. Min Act: -0.1700

Data Index: 8170773 (Open Web Text)

Max Activating Token Index: 92

Click toggle to see full text

Truncated

Full Text #18


Text #19

Max Range: 5.5016. Min Range: -5.5016

Max Act: 5.1579. Min Act: -0.1700

Data Index: 6433497 (Open Web Text)

Max Activating Token Index: 709

Click toggle to see full text

Truncated

Full Text #19