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

Dataset: Open Web Text

Neuron 2382 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: 5.0196. Min Range: -5.0196

Max Act: 5.0196. Min Act: -0.1700

Data Index: 4970838 (Open Web Text)

Max Activating Token Index: 147

Text #1

Max Range: 5.0196. Min Range: -5.0196

Max Act: 5.0188. Min Act: -0.1700

Data Index: 2179299 (Open Web Text)

Max Activating Token Index: 629

Text #2

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9448. Min Act: -0.1700

Data Index: 5352424 (Open Web Text)

Max Activating Token Index: 126

Text #3

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9303. Min Act: -0.1700

Data Index: 1166241 (Open Web Text)

Max Activating Token Index: 405

Text #4

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9222. Min Act: -0.1700

Data Index: 6740666 (Open Web Text)

Max Activating Token Index: 758

Text #5

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9004. Min Act: -0.1700

Data Index: 2173616 (Open Web Text)

Max Activating Token Index: 782

Text #6

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9291. Min Act: -0.1700

Data Index: 1315017 (Open Web Text)

Max Activating Token Index: 358

Text #7

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9132. Min Act: -0.1700

Data Index: 1948106 (Open Web Text)

Max Activating Token Index: 523

Text #8

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9375. Min Act: -0.1700

Data Index: 7095961 (Open Web Text)

Max Activating Token Index: 724

Text #9

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8829. Min Act: -0.1700

Data Index: 2349932 (Open Web Text)

Max Activating Token Index: 687

Text #10

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8870. Min Act: -0.1700

Data Index: 2482388 (Open Web Text)

Max Activating Token Index: 730

Text #11

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.9046. Min Act: -0.1700

Data Index: 7751003 (Open Web Text)

Max Activating Token Index: 37

Text #12

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8759. Min Act: -0.1700

Data Index: 5016221 (Open Web Text)

Max Activating Token Index: 486

Text #13

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8652. Min Act: -0.1700

Data Index: 7342284 (Open Web Text)

Max Activating Token Index: 567

Text #14

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8507. Min Act: -0.1700

Data Index: 3968737 (Open Web Text)

Max Activating Token Index: 19

Text #15

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8605. Min Act: -0.1700

Data Index: 4444366 (Open Web Text)

Max Activating Token Index: 734

Text #16

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8696. Min Act: -0.1700

Data Index: 7480404 (Open Web Text)

Max Activating Token Index: 498

Text #17

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8611. Min Act: -0.1700

Data Index: 1423486 (Open Web Text)

Max Activating Token Index: 815

Text #18

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8495. Min Act: -0.1700

Data Index: 608599 (Open Web Text)

Max Activating Token Index: 836

Text #19

Max Range: 5.0196. Min Range: -5.0196

Max Act: 4.8395. Min Act: -0.1700

Data Index: 8015251 (Open Web Text)

Max Activating Token Index: 54