< Prev | Home | Model | Random | Next >

Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 1996 in Layer 3

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.2017. Min Act: -0.1700

Data Index: 5898795 (Open Web Text)

Max Activating Token Index: 617

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.1543. Min Act: -0.1700

Data Index: 318474 (Open Web Text)

Max Activating Token Index: 573

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.1375. Min Act: -0.1700

Data Index: 5272330 (Open Web Text)

Max Activating Token Index: 131

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.1249. Min Act: -0.1700

Data Index: 474029 (Open Web Text)

Max Activating Token Index: 254

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.1074. Min Act: -0.1700

Data Index: 5419096 (Open Web Text)

Max Activating Token Index: 387

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.1023. Min Act: -0.1700

Data Index: 782284 (Open Web Text)

Max Activating Token Index: 147

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.1003. Min Act: -0.1700

Data Index: 1958412 (Open Web Text)

Max Activating Token Index: 143

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0576. Min Act: -0.1700

Data Index: 4832039 (Open Web Text)

Max Activating Token Index: 856

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0227. Min Act: -0.1700

Data Index: 2871757 (Open Web Text)

Max Activating Token Index: 128

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0626. Min Act: -0.1700

Data Index: 3145134 (Open Web Text)

Max Activating Token Index: 551

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0443. Min Act: -0.1700

Data Index: 1683474 (Open Web Text)

Max Activating Token Index: 582

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0132. Min Act: -0.1700

Data Index: 652355 (Open Web Text)

Max Activating Token Index: 77

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0062. Min Act: -0.1700

Data Index: 308393 (Open Web Text)

Max Activating Token Index: 81

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 4.2017. Min Range: -4.2017

Max Act: 3.9770. Min Act: -0.1700

Data Index: 5621695 (Open Web Text)

Max Activating Token Index: 555

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 4.2017. Min Range: -4.2017

Max Act: 4.0941. Min Act: -0.1700

Data Index: 7524795 (Open Web Text)

Max Activating Token Index: 636

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 4.2017. Min Range: -4.2017

Max Act: 3.9977. Min Act: -0.1700

Data Index: 4868249 (Open Web Text)

Max Activating Token Index: 625

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 4.2017. Min Range: -4.2017

Max Act: 3.9659. Min Act: -0.1700

Data Index: 5850855 (Open Web Text)

Max Activating Token Index: 683

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 4.2017. Min Range: -4.2017

Max Act: 3.9813. Min Act: -0.1700

Data Index: 6593544 (Open Web Text)

Max Activating Token Index: 829

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 4.2017. Min Range: -4.2017

Max Act: 3.9684. Min Act: -0.1700

Data Index: 1578583 (Open Web Text)

Max Activating Token Index: 89

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 4.2017. Min Range: -4.2017

Max Act: 3.9641. Min Act: -0.1700

Data Index: 1811035 (Open Web Text)

Max Activating Token Index: 431

Click toggle to see full text

Truncated

Full Text #19