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

Dataset: Open Web Text

Neuron 1446 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: 3.1000. Min Range: -3.1000

Max Act: 3.1000. Min Act: -0.1700

Data Index: 7839182 (Open Web Text)

Max Activating Token Index: 180

Text #1

Max Range: 3.1000. Min Range: -3.1000

Max Act: 3.0787. Min Act: -0.1700

Data Index: 2887672 (Open Web Text)

Max Activating Token Index: 1012

Text #2

Max Range: 3.1000. Min Range: -3.1000

Max Act: 3.0748. Min Act: -0.1700

Data Index: 3144681 (Open Web Text)

Max Activating Token Index: 432

Text #3

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9988. Min Act: -0.1700

Data Index: 4494230 (Open Web Text)

Max Activating Token Index: 790

Text #4

Max Range: 3.1000. Min Range: -3.1000

Max Act: 3.0400. Min Act: -0.1700

Data Index: 1372191 (Open Web Text)

Max Activating Token Index: 667

Text #5

Max Range: 3.1000. Min Range: -3.1000

Max Act: 3.0181. Min Act: -0.1700

Data Index: 6394421 (Open Web Text)

Max Activating Token Index: 848

Text #6

Max Range: 3.1000. Min Range: -3.1000

Max Act: 3.0109. Min Act: -0.1700

Data Index: 8013030 (Open Web Text)

Max Activating Token Index: 301

Text #7

Max Range: 3.1000. Min Range: -3.1000

Max Act: 3.0119. Min Act: -0.1700

Data Index: 3804318 (Open Web Text)

Max Activating Token Index: 613

Text #8

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9929. Min Act: -0.1700

Data Index: 3449199 (Open Web Text)

Max Activating Token Index: 990

Text #9

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9773. Min Act: -0.1700

Data Index: 5682485 (Open Web Text)

Max Activating Token Index: 610

Text #10

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9920. Min Act: -0.1700

Data Index: 1581350 (Open Web Text)

Max Activating Token Index: 582

Text #11

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9300. Min Act: -0.1700

Data Index: 8163395 (Open Web Text)

Max Activating Token Index: 79

Text #12

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9610. Min Act: -0.1700

Data Index: 6417189 (Open Web Text)

Max Activating Token Index: 201

Text #13

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9559. Min Act: -0.1700

Data Index: 4296167 (Open Web Text)

Max Activating Token Index: 210

Text #14

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9390. Min Act: -0.1700

Data Index: 6377389 (Open Web Text)

Max Activating Token Index: 165

Text #15

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9430. Min Act: -0.1700

Data Index: 3111364 (Open Web Text)

Max Activating Token Index: 166

Text #16

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9660. Min Act: -0.1700

Data Index: 7795693 (Open Web Text)

Max Activating Token Index: 482

Text #17

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9493. Min Act: -0.1700

Data Index: 6089054 (Open Web Text)

Max Activating Token Index: 213

Text #18

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9260. Min Act: -0.1700

Data Index: 530543 (Open Web Text)

Max Activating Token Index: 888

Text #19

Max Range: 3.1000. Min Range: -3.1000

Max Act: 2.9425. Min Act: -0.1700

Data Index: 8304581 (Open Web Text)

Max Activating Token Index: 525