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

Dataset: Open Web Text

Neuron 2383 in Layer 4

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: 4.8422. Min Range: -4.8422

Max Act: 4.8422. Min Act: -0.1700

Data Index: 4064517 (Open Web Text)

Max Activating Token Index: 361

Text #1

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.7305. Min Act: -0.1700

Data Index: 6535512 (Open Web Text)

Max Activating Token Index: 340

Text #2

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.6413. Min Act: -0.1700

Data Index: 625865 (Open Web Text)

Max Activating Token Index: 779

Text #3

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.6226. Min Act: -0.1700

Data Index: 5906183 (Open Web Text)

Max Activating Token Index: 14

Text #4

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5933. Min Act: -0.1700

Data Index: 3664628 (Open Web Text)

Max Activating Token Index: 692

Text #5

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5765. Min Act: -0.1700

Data Index: 7150405 (Open Web Text)

Max Activating Token Index: 922

Text #6

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5649. Min Act: -0.1700

Data Index: 228881 (Open Web Text)

Max Activating Token Index: 489

Text #7

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.6036. Min Act: -0.1700

Data Index: 2880759 (Open Web Text)

Max Activating Token Index: 1005

Text #8

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5844. Min Act: -0.1700

Data Index: 1343103 (Open Web Text)

Max Activating Token Index: 324

Text #9

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.6060. Min Act: -0.1700

Data Index: 8378058 (Open Web Text)

Max Activating Token Index: 345

Text #10

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5521. Min Act: -0.1700

Data Index: 3456162 (Open Web Text)

Max Activating Token Index: 956

Text #11

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5075. Min Act: -0.1700

Data Index: 4931928 (Open Web Text)

Max Activating Token Index: 592

Text #12

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5464. Min Act: -0.1700

Data Index: 1243115 (Open Web Text)

Max Activating Token Index: 224

Text #13

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5384. Min Act: -0.1700

Data Index: 4376133 (Open Web Text)

Max Activating Token Index: 539

Text #14

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5389. Min Act: -0.1700

Data Index: 5961348 (Open Web Text)

Max Activating Token Index: 609

Text #15

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5352. Min Act: -0.1700

Data Index: 5878947 (Open Web Text)

Max Activating Token Index: 350

Text #16

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5390. Min Act: -0.1700

Data Index: 5859010 (Open Web Text)

Max Activating Token Index: 955

Text #17

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5077. Min Act: -0.1700

Data Index: 2977420 (Open Web Text)

Max Activating Token Index: 517

Text #18

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.4473. Min Act: -0.1700

Data Index: 5414118 (Open Web Text)

Max Activating Token Index: 519

Text #19

Max Range: 4.8422. Min Range: -4.8422

Max Act: 4.5124. Min Act: -0.1700

Data Index: 5434053 (Open Web Text)

Max Activating Token Index: 653