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

Dataset: Open Web Text

Neuron 1059 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: 3.3601. Min Range: -3.3601

Max Act: 3.3601. Min Act: -0.1700

Data Index: 5968667 (Open Web Text)

Max Activating Token Index: 796

Text #1

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.3013. Min Act: -0.1700

Data Index: 2452513 (Open Web Text)

Max Activating Token Index: 27

Text #2

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.3038. Min Act: -0.1700

Data Index: 5211424 (Open Web Text)

Max Activating Token Index: 408

Text #3

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2961. Min Act: -0.1700

Data Index: 1304854 (Open Web Text)

Max Activating Token Index: 833

Text #4

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2780. Min Act: -0.1700

Data Index: 1357500 (Open Web Text)

Max Activating Token Index: 39

Text #5

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2729. Min Act: -0.1700

Data Index: 4018170 (Open Web Text)

Max Activating Token Index: 391

Text #6

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2585. Min Act: -0.1700

Data Index: 8649838 (Open Web Text)

Max Activating Token Index: 769

Text #7

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2614. Min Act: -0.1700

Data Index: 1304855 (Open Web Text)

Max Activating Token Index: 139

Text #8

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2487. Min Act: -0.1700

Data Index: 4862841 (Open Web Text)

Max Activating Token Index: 594

Text #9

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2298. Min Act: -0.1700

Data Index: 6235688 (Open Web Text)

Max Activating Token Index: 847

Text #10

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2605. Min Act: -0.1700

Data Index: 5943166 (Open Web Text)

Max Activating Token Index: 410

Text #11

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2330. Min Act: -0.1700

Data Index: 2932866 (Open Web Text)

Max Activating Token Index: 636

Text #12

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2012. Min Act: -0.1700

Data Index: 2528543 (Open Web Text)

Max Activating Token Index: 344

Text #13

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.2121. Min Act: -0.1700

Data Index: 6147800 (Open Web Text)

Max Activating Token Index: 351

Text #14

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.1781. Min Act: -0.1700

Data Index: 7234197 (Open Web Text)

Max Activating Token Index: 489

Text #15

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.1908. Min Act: -0.1700

Data Index: 3214694 (Open Web Text)

Max Activating Token Index: 57

Text #16

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.1879. Min Act: -0.1700

Data Index: 6878004 (Open Web Text)

Max Activating Token Index: 189

Text #17

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1738848 (Open Web Text)

Max Activating Token Index: 1023

Text #18

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.1808. Min Act: -0.1700

Data Index: 2015306 (Open Web Text)

Max Activating Token Index: 30

Text #19

Max Range: 3.3601. Min Range: -3.3601

Max Act: 3.1779. Min Act: -0.1700

Data Index: 3677352 (Open Web Text)

Max Activating Token Index: 674