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

Dataset: Open Web Text

Neuron 820 in Layer 1

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: 4.8342. Min Range: -4.8342

Max Act: 4.8342. Min Act: -0.1700

Data Index: 4844258 (Open Web Text)

Max Activating Token Index: 700

Text #1

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7820. Min Act: -0.1700

Data Index: 2848082 (Open Web Text)

Max Activating Token Index: 572

Text #2

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7901. Min Act: -0.1700

Data Index: 1244256 (Open Web Text)

Max Activating Token Index: 459

Text #3

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7804. Min Act: -0.1700

Data Index: 6136705 (Open Web Text)

Max Activating Token Index: 182

Text #4

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7778. Min Act: -0.1700

Data Index: 8733439 (Open Web Text)

Max Activating Token Index: 531

Text #5

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7688. Min Act: -0.1700

Data Index: 8415024 (Open Web Text)

Max Activating Token Index: 479

Text #6

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7764. Min Act: -0.1700

Data Index: 7752736 (Open Web Text)

Max Activating Token Index: 414

Text #7

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7791. Min Act: -0.1700

Data Index: 7037824 (Open Web Text)

Max Activating Token Index: 458

Text #8

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7651. Min Act: -0.1700

Data Index: 6713404 (Open Web Text)

Max Activating Token Index: 344

Text #9

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7740. Min Act: -0.1700

Data Index: 1972597 (Open Web Text)

Max Activating Token Index: 666

Text #10

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7954. Min Act: -0.1700

Data Index: 6415082 (Open Web Text)

Max Activating Token Index: 315

Text #11

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7780. Min Act: -0.1700

Data Index: 280089 (Open Web Text)

Max Activating Token Index: 742

Text #12

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7572. Min Act: -0.1700

Data Index: 1634261 (Open Web Text)

Max Activating Token Index: 414

Text #13

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7391. Min Act: -0.1699

Data Index: 3277906 (Open Web Text)

Max Activating Token Index: 308

Text #14

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7501. Min Act: -0.1700

Data Index: 3385571 (Open Web Text)

Max Activating Token Index: 696

Text #15

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7364. Min Act: -0.1700

Data Index: 1222677 (Open Web Text)

Max Activating Token Index: 342

Text #16

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7681. Min Act: -0.1700

Data Index: 1270945 (Open Web Text)

Max Activating Token Index: 521

Text #17

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7381. Min Act: -0.1700

Data Index: 1456920 (Open Web Text)

Max Activating Token Index: 711

Text #18

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7589. Min Act: -0.1700

Data Index: 3454311 (Open Web Text)

Max Activating Token Index: 391

Text #19

Max Range: 4.8342. Min Range: -4.8342

Max Act: 4.7686. Min Act: -0.1700

Data Index: 3510918 (Open Web Text)

Max Activating Token Index: 493