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

Dataset: Open Web Text

Neuron 708 in Layer 1

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: 4.3462. Min Range: -4.3462

Max Act: 4.3462. Min Act: -0.1700

Data Index: 7998868 (Open Web Text)

Max Activating Token Index: 151

Text #1

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.3258. Min Act: -0.1700

Data Index: 2015677 (Open Web Text)

Max Activating Token Index: 625

Text #2

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2781. Min Act: -0.1700

Data Index: 1632900 (Open Web Text)

Max Activating Token Index: 180

Text #3

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2884. Min Act: -0.1700

Data Index: 7336000 (Open Web Text)

Max Activating Token Index: 345

Text #4

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2912. Min Act: -0.1700

Data Index: 7304201 (Open Web Text)

Max Activating Token Index: 265

Text #5

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.3040. Min Act: -0.1700

Data Index: 7075084 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2838. Min Act: -0.1700

Data Index: 6859786 (Open Web Text)

Max Activating Token Index: 777

Text #7

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2903. Min Act: -0.1700

Data Index: 4740916 (Open Web Text)

Max Activating Token Index: 636

Text #8

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2980. Min Act: -0.1700

Data Index: 7538192 (Open Web Text)

Max Activating Token Index: 533

Text #9

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.3075. Min Act: -0.1700

Data Index: 7379867 (Open Web Text)

Max Activating Token Index: 740

Text #10

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2832. Min Act: -0.1700

Data Index: 3475866 (Open Web Text)

Max Activating Token Index: 165

Text #11

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2516. Min Act: -0.1700

Data Index: 2038908 (Open Web Text)

Max Activating Token Index: 201

Text #12

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2736. Min Act: -0.1700

Data Index: 527621 (Open Web Text)

Max Activating Token Index: 83

Text #13

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2454. Min Act: -0.1700

Data Index: 5394358 (Open Web Text)

Max Activating Token Index: 835

Text #14

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2673. Min Act: -0.1700

Data Index: 6118883 (Open Web Text)

Max Activating Token Index: 748

Text #15

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2622. Min Act: -0.1700

Data Index: 6346960 (Open Web Text)

Max Activating Token Index: 385

Text #16

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2632. Min Act: -0.1700

Data Index: 6349735 (Open Web Text)

Max Activating Token Index: 546

Text #17

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2696. Min Act: -0.1700

Data Index: 4099282 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2775. Min Act: -0.1700

Data Index: 1229417 (Open Web Text)

Max Activating Token Index: 105

Text #19

Max Range: 4.3462. Min Range: -4.3462

Max Act: 4.2747. Min Act: -0.1700

Data Index: 3458478 (Open Web Text)

Max Activating Token Index: 566