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

Dataset: Open Web Text

Neuron 1194 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: 3.1819. Min Range: -3.1819

Max Act: 3.1819. Min Act: -0.1700

Data Index: 5041121 (Open Web Text)

Max Activating Token Index: 569

Text #1

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1551. Min Act: -0.1700

Data Index: 3631652 (Open Web Text)

Max Activating Token Index: 474

Text #2

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1677. Min Act: -0.1700

Data Index: 7099812 (Open Web Text)

Max Activating Token Index: 429

Text #3

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1215. Min Act: -0.1700

Data Index: 2398073 (Open Web Text)

Max Activating Token Index: 591

Text #4

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1012. Min Act: -0.1700

Data Index: 5285351 (Open Web Text)

Max Activating Token Index: 653

Text #5

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1245. Min Act: -0.1700

Data Index: 7482307 (Open Web Text)

Max Activating Token Index: 503

Text #6

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1282. Min Act: -0.1700

Data Index: 1809240 (Open Web Text)

Max Activating Token Index: 446

Text #7

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1216. Min Act: -0.1700

Data Index: 4568350 (Open Web Text)

Max Activating Token Index: 308

Text #8

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1092. Min Act: -0.1700

Data Index: 4169512 (Open Web Text)

Max Activating Token Index: 527

Text #9

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1113. Min Act: -0.1700

Data Index: 7835008 (Open Web Text)

Max Activating Token Index: 465

Text #10

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0950. Min Act: -0.1700

Data Index: 2961512 (Open Web Text)

Max Activating Token Index: 771

Text #11

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0895. Min Act: -0.1700

Data Index: 1438265 (Open Web Text)

Max Activating Token Index: 591

Text #12

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1035. Min Act: -0.1700

Data Index: 4489368 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1049. Min Act: -0.1700

Data Index: 1658085 (Open Web Text)

Max Activating Token Index: 500

Text #14

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0755. Min Act: -0.1700

Data Index: 1484522 (Open Web Text)

Max Activating Token Index: 965

Text #15

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0696. Min Act: -0.1700

Data Index: 2032919 (Open Web Text)

Max Activating Token Index: 1003

Text #16

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0869. Min Act: -0.1700

Data Index: 7096355 (Open Web Text)

Max Activating Token Index: 25

Text #17

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.1084. Min Act: -0.1700

Data Index: 321802 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0764. Min Act: -0.1700

Data Index: 1394914 (Open Web Text)

Max Activating Token Index: 743

Text #19

Max Range: 3.1819. Min Range: -3.1819

Max Act: 3.0699. Min Act: -0.1700

Data Index: 5945526 (Open Web Text)

Max Activating Token Index: 831