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

Dataset: Open Web Text

Neuron 1552 in Layer 2

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: 4.0183. Min Range: -4.0183

Max Act: 4.0183. Min Act: -0.1700

Data Index: 8153518 (Open Web Text)

Max Activating Token Index: 594

Text #1

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9246. Min Act: -0.1700

Data Index: 35004 (Open Web Text)

Max Activating Token Index: 358

Text #2

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9189. Min Act: -0.1700

Data Index: 2278733 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9317. Min Act: -0.1700

Data Index: 8729093 (Open Web Text)

Max Activating Token Index: 710

Text #4

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9434. Min Act: -0.1700

Data Index: 3418834 (Open Web Text)

Max Activating Token Index: 262

Text #5

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9224. Min Act: -0.1700

Data Index: 2193415 (Open Web Text)

Max Activating Token Index: 710

Text #6

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8857. Min Act: -0.1700

Data Index: 7786271 (Open Web Text)

Max Activating Token Index: 579

Text #7

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9014. Min Act: -0.1700

Data Index: 5209307 (Open Web Text)

Max Activating Token Index: 685

Text #8

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9033. Min Act: -0.1700

Data Index: 3446686 (Open Web Text)

Max Activating Token Index: 946

Text #9

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.9060. Min Act: -0.1700

Data Index: 3193764 (Open Web Text)

Max Activating Token Index: 380

Text #10

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8921. Min Act: -0.1700

Data Index: 7786272 (Open Web Text)

Max Activating Token Index: 798

Text #11

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8372. Min Act: -0.1700

Data Index: 3422549 (Open Web Text)

Max Activating Token Index: 377

Text #12

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8610. Min Act: -0.1700

Data Index: 2988123 (Open Web Text)

Max Activating Token Index: 497

Text #13

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8630. Min Act: -0.1700

Data Index: 862362 (Open Web Text)

Max Activating Token Index: 660

Text #14

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8436. Min Act: -0.1700

Data Index: 2602353 (Open Web Text)

Max Activating Token Index: 795

Text #15

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8779. Min Act: -0.1700

Data Index: 895723 (Open Web Text)

Max Activating Token Index: 930

Text #16

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8738. Min Act: -0.1700

Data Index: 5394944 (Open Web Text)

Max Activating Token Index: 154

Text #17

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8474. Min Act: -0.1700

Data Index: 7259480 (Open Web Text)

Max Activating Token Index: 777

Text #18

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8600. Min Act: -0.1700

Data Index: 2299282 (Open Web Text)

Max Activating Token Index: 727

Text #19

Max Range: 4.0183. Min Range: -4.0183

Max Act: 3.8560. Min Act: -0.1700

Data Index: 1601779 (Open Web Text)

Max Activating Token Index: 265