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

Dataset: Open Web Text

Neuron 2316 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: 4.7417. Min Range: -4.7417

Max Act: 4.6997. Min Act: -0.1700

Data Index: 698752 (Open Web Text)

Max Activating Token Index: 578

Text #1

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.7417. Min Act: -0.1700

Data Index: 5561069 (Open Web Text)

Max Activating Token Index: 986

Text #2

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.6284. Min Act: -0.1700

Data Index: 5170724 (Open Web Text)

Max Activating Token Index: 487

Text #3

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.5652. Min Act: -0.1700

Data Index: 3666908 (Open Web Text)

Max Activating Token Index: 918

Text #4

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.5280. Min Act: -0.1700

Data Index: 189686 (Open Web Text)

Max Activating Token Index: 30

Text #5

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4867. Min Act: -0.1700

Data Index: 8355333 (Open Web Text)

Max Activating Token Index: 873

Text #6

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4566. Min Act: -0.1700

Data Index: 5281113 (Open Web Text)

Max Activating Token Index: 910

Text #7

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4698. Min Act: -0.1700

Data Index: 3557963 (Open Web Text)

Max Activating Token Index: 301

Text #8

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4704. Min Act: -0.1700

Data Index: 5389159 (Open Web Text)

Max Activating Token Index: 771

Text #9

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4838. Min Act: -0.1700

Data Index: 1426948 (Open Web Text)

Max Activating Token Index: 851

Text #10

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4258. Min Act: -0.1700

Data Index: 5473983 (Open Web Text)

Max Activating Token Index: 434

Text #11

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4398. Min Act: -0.1700

Data Index: 6211393 (Open Web Text)

Max Activating Token Index: 686

Text #12

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4121. Min Act: -0.1700

Data Index: 91639 (Open Web Text)

Max Activating Token Index: 263

Text #13

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.3868. Min Act: -0.1700

Data Index: 6419425 (Open Web Text)

Max Activating Token Index: 278

Text #14

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4342. Min Act: -0.1700

Data Index: 7626583 (Open Web Text)

Max Activating Token Index: 420

Text #15

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4192. Min Act: -0.1700

Data Index: 7406976 (Open Web Text)

Max Activating Token Index: 68

Text #16

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4100. Min Act: -0.1700

Data Index: 6623272 (Open Web Text)

Max Activating Token Index: 133

Text #17

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.4045. Min Act: -0.1700

Data Index: 1562469 (Open Web Text)

Max Activating Token Index: 804

Text #18

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.3863. Min Act: -0.1700

Data Index: 1961929 (Open Web Text)

Max Activating Token Index: 39

Text #19

Max Range: 4.7417. Min Range: -4.7417

Max Act: 4.3684. Min Act: -0.1700

Data Index: 1319477 (Open Web Text)

Max Activating Token Index: 784