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

Dataset: Open Web Text

Neuron 834 in Layer 5

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: 3.0248. Min Range: -3.0248

Max Act: 3.0248. Min Act: -0.1700

Data Index: 7539502 (Open Web Text)

Max Activating Token Index: 442

Text #1

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.8320. Min Act: -0.1696

Data Index: 6280534 (Open Web Text)

Max Activating Token Index: 601

Text #2

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.7949. Min Act: -0.1700

Data Index: 4067028 (Open Web Text)

Max Activating Token Index: 984

Text #3

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.8006. Min Act: -0.1698

Data Index: 3318682 (Open Web Text)

Max Activating Token Index: 152

Text #4

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.7644. Min Act: -0.1251

Data Index: 1647418 (Open Web Text)

Max Activating Token Index: 672

Text #5

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.7741. Min Act: -0.1679

Data Index: 7969110 (Open Web Text)

Max Activating Token Index: 688

Text #6

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.7498. Min Act: -0.1658

Data Index: 7666733 (Open Web Text)

Max Activating Token Index: 461

Text #7

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.7339. Min Act: -0.0267

Data Index: 7653327 (Open Web Text)

Max Activating Token Index: 406

Text #8

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.7185. Min Act: -0.1700

Data Index: 5658717 (Open Web Text)

Max Activating Token Index: 301

Text #9

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6950. Min Act: -0.1699

Data Index: 8128436 (Open Web Text)

Max Activating Token Index: 801

Text #10

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6955. Min Act: -0.1700

Data Index: 5412711 (Open Web Text)

Max Activating Token Index: 966

Text #11

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6845. Min Act: -0.1700

Data Index: 4482734 (Open Web Text)

Max Activating Token Index: 414

Text #12

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6657. Min Act: -0.1667

Data Index: 7430373 (Open Web Text)

Max Activating Token Index: 790

Text #13

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6707. Min Act: -0.1699

Data Index: 1275022 (Open Web Text)

Max Activating Token Index: 701

Text #14

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6561. Min Act: -0.1700

Data Index: 2716478 (Open Web Text)

Max Activating Token Index: 382

Text #15

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6675. Min Act: -0.1674

Data Index: 2962565 (Open Web Text)

Max Activating Token Index: 341

Text #16

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6565. Min Act: -0.1677

Data Index: 390154 (Open Web Text)

Max Activating Token Index: 919

Text #17

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6636. Min Act: -0.1698

Data Index: 1400601 (Open Web Text)

Max Activating Token Index: 891

Text #18

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6540. Min Act: -0.1693

Data Index: 4443567 (Open Web Text)

Max Activating Token Index: 939

Text #19

Max Range: 3.0248. Min Range: -3.0248

Max Act: 2.6536. Min Act: -0.1699

Data Index: 1518297 (Open Web Text)

Max Activating Token Index: 574