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

Dataset: Open Web Text

Neuron 1500 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: 6.1454. Min Range: -6.1454

Max Act: 6.1454. Min Act: -0.1700

Data Index: 1759569 (Open Web Text)

Max Activating Token Index: 833

Text #1

Max Range: 6.1454. Min Range: -6.1454

Max Act: 6.0471. Min Act: -0.1700

Data Index: 6301567 (Open Web Text)

Max Activating Token Index: 269

Text #2

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.9373. Min Act: -0.1700

Data Index: 8492712 (Open Web Text)

Max Activating Token Index: 924

Text #3

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.9599. Min Act: -0.1700

Data Index: 7321667 (Open Web Text)

Max Activating Token Index: 938

Text #4

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.9955. Min Act: -0.1700

Data Index: 7273142 (Open Web Text)

Max Activating Token Index: 618

Text #5

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.9320. Min Act: -0.1700

Data Index: 1268223 (Open Web Text)

Max Activating Token Index: 326

Text #6

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.9080. Min Act: -0.1700

Data Index: 3778058 (Open Web Text)

Max Activating Token Index: 226

Text #7

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8898. Min Act: -0.1700

Data Index: 2464982 (Open Web Text)

Max Activating Token Index: 682

Text #8

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8772. Min Act: -0.1700

Data Index: 8634642 (Open Web Text)

Max Activating Token Index: 461

Text #9

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8438. Min Act: -0.1700

Data Index: 2897887 (Open Web Text)

Max Activating Token Index: 385

Text #10

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8730. Min Act: -0.1700

Data Index: 2555686 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8447. Min Act: -0.1700

Data Index: 5582619 (Open Web Text)

Max Activating Token Index: 160

Text #12

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8257. Min Act: -0.1700

Data Index: 6597615 (Open Web Text)

Max Activating Token Index: 109

Text #13

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8362. Min Act: -0.1700

Data Index: 227154 (Open Web Text)

Max Activating Token Index: 909

Text #14

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8284. Min Act: -0.1700

Data Index: 8624406 (Open Web Text)

Max Activating Token Index: 222

Text #15

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.7919. Min Act: -0.1700

Data Index: 5854427 (Open Web Text)

Max Activating Token Index: 581

Text #16

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.7912. Min Act: -0.1700

Data Index: 8631945 (Open Web Text)

Max Activating Token Index: 545

Text #17

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.8001. Min Act: -0.1700

Data Index: 6128177 (Open Web Text)

Max Activating Token Index: 523

Text #18

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.7496. Min Act: -0.1700

Data Index: 2264144 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 6.1454. Min Range: -6.1454

Max Act: 5.7638. Min Act: -0.1700

Data Index: 5754779 (Open Web Text)

Max Activating Token Index: 514