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

Dataset: Open Web Text

Neuron 2184 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: 5.0556. Min Range: -5.0556

Max Act: 5.0556. Min Act: -0.1700

Data Index: 332084 (Open Web Text)

Max Activating Token Index: 924

Text #1

Max Range: 5.0556. Min Range: -5.0556

Max Act: 5.0223. Min Act: -0.1700

Data Index: 1458402 (Open Web Text)

Max Activating Token Index: 210

Text #2

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9856. Min Act: -0.1700

Data Index: 2473990 (Open Web Text)

Max Activating Token Index: 509

Text #3

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9958. Min Act: -0.1700

Data Index: 6852298 (Open Web Text)

Max Activating Token Index: 479

Text #4

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9919. Min Act: -0.1700

Data Index: 2437118 (Open Web Text)

Max Activating Token Index: 299

Text #5

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9885. Min Act: -0.1700

Data Index: 2340301 (Open Web Text)

Max Activating Token Index: 302

Text #6

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9900. Min Act: -0.1700

Data Index: 2793541 (Open Web Text)

Max Activating Token Index: 923

Text #7

Max Range: 5.0556. Min Range: -5.0556

Max Act: 5.0200. Min Act: -0.1700

Data Index: 5821391 (Open Web Text)

Max Activating Token Index: 900

Text #8

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9569. Min Act: -0.1700

Data Index: 2821654 (Open Web Text)

Max Activating Token Index: 427

Text #9

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9777. Min Act: -0.1700

Data Index: 1788938 (Open Web Text)

Max Activating Token Index: 537

Text #10

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9803. Min Act: -0.1700

Data Index: 4890140 (Open Web Text)

Max Activating Token Index: 665

Text #11

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9271. Min Act: -0.1700

Data Index: 6613507 (Open Web Text)

Max Activating Token Index: 786

Text #12

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9417. Min Act: -0.1700

Data Index: 2968447 (Open Web Text)

Max Activating Token Index: 816

Text #13

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9254. Min Act: -0.1700

Data Index: 2148478 (Open Web Text)

Max Activating Token Index: 844

Text #14

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9372. Min Act: -0.1700

Data Index: 4275125 (Open Web Text)

Max Activating Token Index: 513

Text #15

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9328. Min Act: -0.1700

Data Index: 542261 (Open Web Text)

Max Activating Token Index: 24

Text #16

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9189. Min Act: -0.1700

Data Index: 5503826 (Open Web Text)

Max Activating Token Index: 741

Text #17

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9420. Min Act: -0.1700

Data Index: 763894 (Open Web Text)

Max Activating Token Index: 956

Text #18

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9508. Min Act: -0.1700

Data Index: 7395761 (Open Web Text)

Max Activating Token Index: 554

Text #19

Max Range: 5.0556. Min Range: -5.0556

Max Act: 4.9104. Min Act: -0.1700

Data Index: 129439 (Open Web Text)

Max Activating Token Index: 359