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

Dataset: Open Web Text

Neuron 102 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: 2.9331. Min Range: -2.9331

Max Act: 2.9331. Min Act: -0.1700

Data Index: 1123640 (Open Web Text)

Max Activating Token Index: 804

Text #1

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.8722. Min Act: -0.1700

Data Index: 8767413 (Open Web Text)

Max Activating Token Index: 173

Text #2

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.8094. Min Act: -0.1700

Data Index: 5551436 (Open Web Text)

Max Activating Token Index: 780

Text #3

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7887. Min Act: -0.1700

Data Index: 5713649 (Open Web Text)

Max Activating Token Index: 732

Text #4

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7914. Min Act: -0.1700

Data Index: 6809141 (Open Web Text)

Max Activating Token Index: 483

Text #5

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.8037. Min Act: -0.1700

Data Index: 1230702 (Open Web Text)

Max Activating Token Index: 109

Text #6

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.8130. Min Act: -0.1700

Data Index: 1491025 (Open Web Text)

Max Activating Token Index: 493

Text #7

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.8060. Min Act: -0.1700

Data Index: 7150714 (Open Web Text)

Max Activating Token Index: 36

Text #8

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7856. Min Act: -0.1700

Data Index: 5275789 (Open Web Text)

Max Activating Token Index: 675

Text #9

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7748. Min Act: -0.1700

Data Index: 2264904 (Open Web Text)

Max Activating Token Index: 533

Text #10

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7597. Min Act: -0.1700

Data Index: 7919943 (Open Web Text)

Max Activating Token Index: 777

Text #11

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7401. Min Act: -0.1700

Data Index: 6046936 (Open Web Text)

Max Activating Token Index: 918

Text #12

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7421. Min Act: -0.1700

Data Index: 4094153 (Open Web Text)

Max Activating Token Index: 15

Text #13

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7453. Min Act: -0.1700

Data Index: 4736381 (Open Web Text)

Max Activating Token Index: 935

Text #14

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7183. Min Act: -0.1700

Data Index: 2079110 (Open Web Text)

Max Activating Token Index: 846

Text #15

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7212. Min Act: -0.1700

Data Index: 5974465 (Open Web Text)

Max Activating Token Index: 688

Text #16

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.6967. Min Act: -0.1700

Data Index: 5105627 (Open Web Text)

Max Activating Token Index: 703

Text #17

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.6910. Min Act: -0.1700

Data Index: 2431402 (Open Web Text)

Max Activating Token Index: 179

Text #18

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.7114. Min Act: -0.1700

Data Index: 5845148 (Open Web Text)

Max Activating Token Index: 16

Text #19

Max Range: 2.9331. Min Range: -2.9331

Max Act: 2.6891. Min Act: -0.1700

Data Index: 2268150 (Open Web Text)

Max Activating Token Index: 696