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

Dataset: Open Web Text

Neuron 1736 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: 3.7050. Min Range: -3.7050

Max Act: 3.7050. Min Act: -0.1700

Data Index: 2014878 (Open Web Text)

Max Activating Token Index: 286

Text #1

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.6504. Min Act: -0.1700

Data Index: 8771214 (Open Web Text)

Max Activating Token Index: 895

Text #2

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.6121. Min Act: -0.1700

Data Index: 4013976 (Open Web Text)

Max Activating Token Index: 794

Text #3

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5817. Min Act: -0.1700

Data Index: 3363563 (Open Web Text)

Max Activating Token Index: 745

Text #4

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5731. Min Act: -0.1700

Data Index: 3093008 (Open Web Text)

Max Activating Token Index: 780

Text #5

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5775. Min Act: -0.1700

Data Index: 825822 (Open Web Text)

Max Activating Token Index: 82

Text #6

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5159. Min Act: -0.1700

Data Index: 8771213 (Open Web Text)

Max Activating Token Index: 859

Text #7

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5401. Min Act: -0.1700

Data Index: 7073090 (Open Web Text)

Max Activating Token Index: 466

Text #8

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5286. Min Act: -0.1700

Data Index: 7478378 (Open Web Text)

Max Activating Token Index: 959

Text #9

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.5026. Min Act: -0.1700

Data Index: 6949166 (Open Web Text)

Max Activating Token Index: 503

Text #10

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4652. Min Act: -0.1700

Data Index: 4626473 (Open Web Text)

Max Activating Token Index: 875

Text #11

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4797. Min Act: -0.1700

Data Index: 8082646 (Open Web Text)

Max Activating Token Index: 441

Text #12

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4717. Min Act: -0.1700

Data Index: 6269978 (Open Web Text)

Max Activating Token Index: 961

Text #13

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4848. Min Act: -0.1700

Data Index: 1976764 (Open Web Text)

Max Activating Token Index: 395

Text #14

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4580. Min Act: -0.1700

Data Index: 690189 (Open Web Text)

Max Activating Token Index: 393

Text #15

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4373. Min Act: -0.1700

Data Index: 1652695 (Open Web Text)

Max Activating Token Index: 620

Text #16

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4325. Min Act: -0.1700

Data Index: 3532985 (Open Web Text)

Max Activating Token Index: 588

Text #17

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4861. Min Act: -0.1700

Data Index: 631443 (Open Web Text)

Max Activating Token Index: 361

Text #18

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4660. Min Act: -0.1700

Data Index: 589887 (Open Web Text)

Max Activating Token Index: 213

Text #19

Max Range: 3.7050. Min Range: -3.7050

Max Act: 3.4617. Min Act: -0.1700

Data Index: 5641696 (Open Web Text)

Max Activating Token Index: 691