< Prev | Home | Model | Random | Next >

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

Dataset: Open Web Text

Neuron 322 in Layer 6

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: 2.6550. Min Range: -2.6550

Max Act: 2.6550. Min Act: -0.1700

Data Index: 7259898 (Open Web Text)

Max Activating Token Index: 282

Click toggle to see full text

Truncated

Full Text #0

Text #1

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.6423. Min Act: -0.1700

Data Index: 3800105 (Open Web Text)

Max Activating Token Index: 907

Click toggle to see full text

Truncated

Full Text #1

Text #2

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.6314. Min Act: -0.1700

Data Index: 8226644 (Open Web Text)

Max Activating Token Index: 18

Click toggle to see full text

Truncated

Full Text #2

Text #3

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.6061. Min Act: -0.1700

Data Index: 4396362 (Open Web Text)

Max Activating Token Index: 159

Click toggle to see full text

Truncated

Full Text #3

Text #4

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5893. Min Act: -0.1700

Data Index: 497624 (Open Web Text)

Max Activating Token Index: 828

Click toggle to see full text

Truncated

Full Text #4

Text #5

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5713. Min Act: -0.1700

Data Index: 1436353 (Open Web Text)

Max Activating Token Index: 592

Click toggle to see full text

Truncated

Full Text #5

Text #6

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5429. Min Act: -0.1700

Data Index: 1362174 (Open Web Text)

Max Activating Token Index: 405

Click toggle to see full text

Truncated

Full Text #6

Text #7

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5478. Min Act: -0.1700

Data Index: 212302 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #7

Text #8

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5110. Min Act: -0.1700

Data Index: 8403052 (Open Web Text)

Max Activating Token Index: 457

Click toggle to see full text

Truncated

Full Text #8

Text #9

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5107. Min Act: -0.1700

Data Index: 3814019 (Open Web Text)

Max Activating Token Index: 303

Click toggle to see full text

Truncated

Full Text #9

Text #10

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5029. Min Act: -0.1700

Data Index: 4251450 (Open Web Text)

Max Activating Token Index: 905

Click toggle to see full text

Truncated

Full Text #10

Text #11

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5095. Min Act: -0.1700

Data Index: 1774699 (Open Web Text)

Max Activating Token Index: 269

Click toggle to see full text

Truncated

Full Text #11

Text #12

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5157. Min Act: -0.1700

Data Index: 5443875 (Open Web Text)

Max Activating Token Index: 240

Click toggle to see full text

Truncated

Full Text #12

Text #13

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.5317. Min Act: -0.1700

Data Index: 2295190 (Open Web Text)

Max Activating Token Index: 618

Click toggle to see full text

Truncated

Full Text #13

Text #14

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.4909. Min Act: -0.1700

Data Index: 5952918 (Open Web Text)

Max Activating Token Index: 942

Click toggle to see full text

Truncated

Full Text #14

Text #15

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.4999. Min Act: -0.1700

Data Index: 8323109 (Open Web Text)

Max Activating Token Index: 715

Click toggle to see full text

Truncated

Full Text #15

Text #16

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.4929. Min Act: -0.1700

Data Index: 2809000 (Open Web Text)

Max Activating Token Index: 322

Click toggle to see full text

Truncated

Full Text #16

Text #17

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.4954. Min Act: -0.1700

Data Index: 6501514 (Open Web Text)

Max Activating Token Index: 974

Click toggle to see full text

Truncated

Full Text #17

Text #18

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.4986. Min Act: -0.1700

Data Index: 4048327 (Open Web Text)

Max Activating Token Index: 621

Click toggle to see full text

Truncated

Full Text #18

Text #19

Max Range: 2.6550. Min Range: -2.6550

Max Act: 2.4947. Min Act: -0.1700

Data Index: 4282528 (Open Web Text)

Max Activating Token Index: 697

Click toggle to see full text

Truncated

Full Text #19