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

Dataset: Open Web Text

Neuron 2369 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: 5.4502. Min Range: -5.4502

Max Act: 5.4502. Min Act: -0.1700

Data Index: 7918833 (Open Web Text)

Max Activating Token Index: 591

Text #1

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.3568. Min Act: -0.1700

Data Index: 4380472 (Open Web Text)

Max Activating Token Index: 487

Text #2

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2943. Min Act: -0.1700

Data Index: 6621790 (Open Web Text)

Max Activating Token Index: 215

Text #3

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.3216. Min Act: -0.1700

Data Index: 7774040 (Open Web Text)

Max Activating Token Index: 667

Text #4

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.3212. Min Act: -0.1700

Data Index: 2297274 (Open Web Text)

Max Activating Token Index: 650

Text #5

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2864. Min Act: -0.1700

Data Index: 6847320 (Open Web Text)

Max Activating Token Index: 523

Text #6

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2659. Min Act: -0.1700

Data Index: 8372313 (Open Web Text)

Max Activating Token Index: 107

Text #7

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2959. Min Act: -0.1700

Data Index: 8268757 (Open Web Text)

Max Activating Token Index: 354

Text #8

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2890. Min Act: -0.1700

Data Index: 3896130 (Open Web Text)

Max Activating Token Index: 518

Text #9

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2869. Min Act: -0.1700

Data Index: 6439247 (Open Web Text)

Max Activating Token Index: 688

Text #10

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2682. Min Act: -0.1700

Data Index: 6016445 (Open Web Text)

Max Activating Token Index: 209

Text #11

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2827. Min Act: -0.1700

Data Index: 3765304 (Open Web Text)

Max Activating Token Index: 475

Text #12

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2523. Min Act: -0.1700

Data Index: 7217491 (Open Web Text)

Max Activating Token Index: 804

Text #13

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2769. Min Act: -0.1700

Data Index: 7596347 (Open Web Text)

Max Activating Token Index: 712

Text #14

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2473. Min Act: -0.1700

Data Index: 2350468 (Open Web Text)

Max Activating Token Index: 621

Text #15

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2771. Min Act: -0.1700

Data Index: 4452109 (Open Web Text)

Max Activating Token Index: 374

Text #16

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2581. Min Act: -0.1700

Data Index: 8083967 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2624. Min Act: -0.1700

Data Index: 4717936 (Open Web Text)

Max Activating Token Index: 76

Text #18

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2654. Min Act: -0.1700

Data Index: 2846191 (Open Web Text)

Max Activating Token Index: 555

Text #19

Max Range: 5.4502. Min Range: -5.4502

Max Act: 5.2602. Min Act: -0.1700

Data Index: 2696446 (Open Web Text)

Max Activating Token Index: 859