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

Dataset: Open Web Text

Neuron 30 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: 4.0130. Min Range: -4.0130

Max Act: 4.0130. Min Act: -0.1700

Data Index: 282000 (Open Web Text)

Max Activating Token Index: 819

Text #1

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.8908. Min Act: -0.1700

Data Index: 5821078 (Open Web Text)

Max Activating Token Index: 890

Text #2

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.7916. Min Act: -0.1700

Data Index: 7878636 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.8126. Min Act: -0.1700

Data Index: 2418621 (Open Web Text)

Max Activating Token Index: 912

Text #4

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.7699. Min Act: -0.1700

Data Index: 2852411 (Open Web Text)

Max Activating Token Index: 702

Text #5

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.7008. Min Act: -0.1700

Data Index: 5527555 (Open Web Text)

Max Activating Token Index: 926

Text #6

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.7323. Min Act: -0.1700

Data Index: 7307102 (Open Web Text)

Max Activating Token Index: 843

Text #7

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.6863. Min Act: -0.1700

Data Index: 1040998 (Open Web Text)

Max Activating Token Index: 671

Text #8

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.6375. Min Act: -0.1700

Data Index: 5541047 (Open Web Text)

Max Activating Token Index: 374

Text #9

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.6559. Min Act: -0.1700

Data Index: 1432384 (Open Web Text)

Max Activating Token Index: 470

Text #10

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.6146. Min Act: -0.1700

Data Index: 7710658 (Open Web Text)

Max Activating Token Index: 327

Text #11

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.6458. Min Act: -0.1700

Data Index: 5945213 (Open Web Text)

Max Activating Token Index: 984

Text #12

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5823. Min Act: -0.1700

Data Index: 674348 (Open Web Text)

Max Activating Token Index: 940

Text #13

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5797. Min Act: -0.1700

Data Index: 5306527 (Open Web Text)

Max Activating Token Index: 321

Text #14

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5813. Min Act: -0.1700

Data Index: 5225028 (Open Web Text)

Max Activating Token Index: 718

Text #15

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5821. Min Act: -0.1700

Data Index: 4305451 (Open Web Text)

Max Activating Token Index: 540

Text #16

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5342. Min Act: -0.1700

Data Index: 3229809 (Open Web Text)

Max Activating Token Index: 921

Text #17

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5373. Min Act: -0.1700

Data Index: 2740343 (Open Web Text)

Max Activating Token Index: 455

Text #18

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5233. Min Act: -0.1700

Data Index: 4028364 (Open Web Text)

Max Activating Token Index: 474

Text #19

Max Range: 4.0130. Min Range: -4.0130

Max Act: 3.5522. Min Act: -0.1700

Data Index: 2706277 (Open Web Text)

Max Activating Token Index: 580