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

Dataset: Open Web Text

Neuron 1099 in Layer 4

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: 3.1361. Min Range: -3.1361

Max Act: 3.0906. Min Act: -0.1700

Data Index: 755504 (Open Web Text)

Max Activating Token Index: 671

Text #1

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.1361. Min Act: -0.1700

Data Index: 6923850 (Open Web Text)

Max Activating Token Index: 932

Text #2

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.1130. Min Act: -0.1700

Data Index: 7453108 (Open Web Text)

Max Activating Token Index: 655

Text #3

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0747. Min Act: -0.1700

Data Index: 3400416 (Open Web Text)

Max Activating Token Index: 432

Text #4

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0647. Min Act: -0.1700

Data Index: 7040673 (Open Web Text)

Max Activating Token Index: 545

Text #5

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0692. Min Act: -0.1700

Data Index: 5771640 (Open Web Text)

Max Activating Token Index: 653

Text #6

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0444. Min Act: -0.1700

Data Index: 6259281 (Open Web Text)

Max Activating Token Index: 77

Text #7

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0534. Min Act: -0.1700

Data Index: 7678781 (Open Web Text)

Max Activating Token Index: 182

Text #8

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0867. Min Act: -0.1700

Data Index: 7282190 (Open Web Text)

Max Activating Token Index: 921

Text #9

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0512. Min Act: -0.1700

Data Index: 5537408 (Open Web Text)

Max Activating Token Index: 132

Text #10

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0302. Min Act: -0.1700

Data Index: 5478420 (Open Web Text)

Max Activating Token Index: 104

Text #11

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0611. Min Act: -0.1700

Data Index: 8762886 (Open Web Text)

Max Activating Token Index: 988

Text #12

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0720. Min Act: -0.1700

Data Index: 747575 (Open Web Text)

Max Activating Token Index: 403

Text #13

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0354. Min Act: -0.1700

Data Index: 1448701 (Open Web Text)

Max Activating Token Index: 100

Text #14

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0342. Min Act: -0.1700

Data Index: 3784964 (Open Web Text)

Max Activating Token Index: 343

Text #15

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0289. Min Act: -0.1700

Data Index: 5083971 (Open Web Text)

Max Activating Token Index: 189

Text #16

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0386. Min Act: -0.1700

Data Index: 144410 (Open Web Text)

Max Activating Token Index: 804

Text #17

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0114. Min Act: -0.1700

Data Index: 5929483 (Open Web Text)

Max Activating Token Index: 405

Text #18

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0003. Min Act: -0.1700

Data Index: 4129839 (Open Web Text)

Max Activating Token Index: 577

Text #19

Max Range: 3.1361. Min Range: -3.1361

Max Act: 3.0258. Min Act: -0.1700

Data Index: 4656367 (Open Web Text)

Max Activating Token Index: 946