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

Dataset: Open Web Text

Neuron 426 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: 4.4656. Min Range: -4.4656

Max Act: 4.4656. Min Act: -0.1700

Data Index: 8501144 (Open Web Text)

Max Activating Token Index: 814

Text #1

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.4511. Min Act: -0.1700

Data Index: 1646360 (Open Web Text)

Max Activating Token Index: 731

Text #2

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.4458. Min Act: -0.1700

Data Index: 4234529 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.4074. Min Act: -0.1700

Data Index: 2694685 (Open Web Text)

Max Activating Token Index: 247

Text #4

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.4055. Min Act: -0.1700

Data Index: 7097314 (Open Web Text)

Max Activating Token Index: 427

Text #5

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3914. Min Act: -0.1700

Data Index: 40137 (Open Web Text)

Max Activating Token Index: 194

Text #6

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3474. Min Act: -0.1700

Data Index: 2517271 (Open Web Text)

Max Activating Token Index: 227

Text #7

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3504. Min Act: -0.1700

Data Index: 925559 (Open Web Text)

Max Activating Token Index: 111

Text #8

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3631. Min Act: -0.1700

Data Index: 4010677 (Open Web Text)

Max Activating Token Index: 770

Text #9

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3568. Min Act: -0.1700

Data Index: 6432816 (Open Web Text)

Max Activating Token Index: 573

Text #10

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3710. Min Act: -0.1700

Data Index: 3169393 (Open Web Text)

Max Activating Token Index: 497

Text #11

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3394. Min Act: -0.1700

Data Index: 2964365 (Open Web Text)

Max Activating Token Index: 352

Text #12

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3570. Min Act: -0.1700

Data Index: 763747 (Open Web Text)

Max Activating Token Index: 142

Text #13

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3400. Min Act: -0.1700

Data Index: 6600132 (Open Web Text)

Max Activating Token Index: 461

Text #14

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3282. Min Act: -0.1700

Data Index: 1989879 (Open Web Text)

Max Activating Token Index: 453

Text #15

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3347. Min Act: -0.1700

Data Index: 4261757 (Open Web Text)

Max Activating Token Index: 388

Text #16

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3114. Min Act: -0.1700

Data Index: 7083717 (Open Web Text)

Max Activating Token Index: 306

Text #17

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3087. Min Act: -0.1700

Data Index: 783061 (Open Web Text)

Max Activating Token Index: 799

Text #18

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3299. Min Act: -0.1700

Data Index: 4962326 (Open Web Text)

Max Activating Token Index: 677

Text #19

Max Range: 4.4656. Min Range: -4.4656

Max Act: 4.3250. Min Act: -0.1700

Data Index: 2499133 (Open Web Text)

Max Activating Token Index: 679