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

Dataset: Open Web Text

Neuron 1971 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: 3.0699. Min Range: -3.0699

Max Act: 3.0699. Min Act: -0.1700

Data Index: 341869 (Open Web Text)

Max Activating Token Index: 670

Text #1

Max Range: 3.0699. Min Range: -3.0699

Max Act: 3.0436. Min Act: -0.1700

Data Index: 341865 (Open Web Text)

Max Activating Token Index: 467

Text #2

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.9363. Min Act: -0.1700

Data Index: 6557463 (Open Web Text)

Max Activating Token Index: 657

Text #3

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.9398. Min Act: -0.1700

Data Index: 341864 (Open Web Text)

Max Activating Token Index: 566

Text #4

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.8985. Min Act: -0.1700

Data Index: 6557462 (Open Web Text)

Max Activating Token Index: 971

Text #5

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.8541. Min Act: -0.1700

Data Index: 6046495 (Open Web Text)

Max Activating Token Index: 448

Text #6

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.8550. Min Act: -0.1700

Data Index: 341866 (Open Web Text)

Max Activating Token Index: 372

Text #7

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.8279. Min Act: -0.1700

Data Index: 341867 (Open Web Text)

Max Activating Token Index: 343

Text #8

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.8039. Min Act: -0.1700

Data Index: 6033203 (Open Web Text)

Max Activating Token Index: 168

Text #9

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.7929. Min Act: -0.1700

Data Index: 6046496 (Open Web Text)

Max Activating Token Index: 412

Text #10

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.7310. Min Act: -0.1700

Data Index: 6046494 (Open Web Text)

Max Activating Token Index: 460

Text #11

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.7362. Min Act: -0.1700

Data Index: 6176351 (Open Web Text)

Max Activating Token Index: 380

Text #12

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6785. Min Act: -0.1700

Data Index: 4551943 (Open Web Text)

Max Activating Token Index: 965

Text #13

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6675. Min Act: -0.1700

Data Index: 886868 (Open Web Text)

Max Activating Token Index: 447

Text #14

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6822. Min Act: -0.1700

Data Index: 7822955 (Open Web Text)

Max Activating Token Index: 296

Text #15

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6706. Min Act: -0.1700

Data Index: 6176353 (Open Web Text)

Max Activating Token Index: 401

Text #16

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6310. Min Act: -0.1700

Data Index: 3688652 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6414. Min Act: -0.1700

Data Index: 3320876 (Open Web Text)

Max Activating Token Index: 319

Text #18

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6559. Min Act: -0.1700

Data Index: 1941917 (Open Web Text)

Max Activating Token Index: 778

Text #19

Max Range: 3.0699. Min Range: -3.0699

Max Act: 2.6383. Min Act: -0.1700

Data Index: 6640351 (Open Web Text)

Max Activating Token Index: 882