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

Dataset: Open Web Text

Neuron 2996 in Layer 0

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: 1.4248. Min Range: -1.4248

Max Act: 1.4248. Min Act: -0.0958

Data Index: 5554446 (Open Web Text)

Max Activating Token Index: 561

Text #1

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.4245. Min Act: -0.1571

Data Index: 6824343 (Open Web Text)

Max Activating Token Index: 392

Text #2

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3997. Min Act: -0.1032

Data Index: 5865145 (Open Web Text)

Max Activating Token Index: 994

Text #3

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.4087. Min Act: -0.1258

Data Index: 3941119 (Open Web Text)

Max Activating Token Index: 901

Text #4

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.4054. Min Act: -0.1481

Data Index: 2634211 (Open Web Text)

Max Activating Token Index: 956

Text #5

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3906. Min Act: -0.0254

Data Index: 4491696 (Open Web Text)

Max Activating Token Index: 393

Text #6

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3906. Min Act: -0.1335

Data Index: 1050391 (Open Web Text)

Max Activating Token Index: 365

Text #7

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3903. Min Act: -0.1450

Data Index: 5990561 (Open Web Text)

Max Activating Token Index: 334

Text #8

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3836. Min Act: -0.1130

Data Index: 898533 (Open Web Text)

Max Activating Token Index: 402

Text #9

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3893. Min Act: -0.0747

Data Index: 8085045 (Open Web Text)

Max Activating Token Index: 393

Text #10

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3834. Min Act: -0.0650

Data Index: 607683 (Open Web Text)

Max Activating Token Index: 95

Text #11

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3811. Min Act: -0.1379

Data Index: 6132232 (Open Web Text)

Max Activating Token Index: 553

Text #12

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3777. Min Act: -0.0395

Data Index: 1643538 (Open Web Text)

Max Activating Token Index: 334

Text #13

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3806. Min Act: -0.0640

Data Index: 6597159 (Open Web Text)

Max Activating Token Index: 388

Text #14

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3731. Min Act: -0.1276

Data Index: 308535 (Open Web Text)

Max Activating Token Index: 331

Text #15

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3753. Min Act: -0.0945

Data Index: 3163420 (Open Web Text)

Max Activating Token Index: 448

Text #16

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3738. Min Act: -0.1136

Data Index: 4599287 (Open Web Text)

Max Activating Token Index: 510

Text #17

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3731. Min Act: -0.0785

Data Index: 4903985 (Open Web Text)

Max Activating Token Index: 619

Text #18

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3715. Min Act: -0.1622

Data Index: 5143237 (Open Web Text)

Max Activating Token Index: 212

Text #19

Max Range: 1.4248. Min Range: -1.4248

Max Act: 1.3758. Min Act: -0.1185

Data Index: 1987500 (Open Web Text)

Max Activating Token Index: 367