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

Dataset: Open Web Text

Neuron 1868 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: 1.8625. Min Range: -1.8625

Max Act: 1.8625. Min Act: -0.1700

Data Index: 5697464 (Open Web Text)

Max Activating Token Index: 21

Text #1

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8611. Min Act: -0.1699

Data Index: 1293236 (Open Web Text)

Max Activating Token Index: 222

Text #2

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8472. Min Act: -0.1700

Data Index: 3946326 (Open Web Text)

Max Activating Token Index: 895

Text #3

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.8252. Min Act: -0.1700

Data Index: 332618 (Open Web Text)

Max Activating Token Index: 482

Text #4

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7773. Min Act: -0.1700

Data Index: 4111739 (Open Web Text)

Max Activating Token Index: 841

Text #5

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7782. Min Act: -0.1700

Data Index: 4813592 (Open Web Text)

Max Activating Token Index: 825

Text #6

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7496. Min Act: -0.1700

Data Index: 6782266 (Open Web Text)

Max Activating Token Index: 146

Text #7

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7546. Min Act: -0.1700

Data Index: 4986248 (Open Web Text)

Max Activating Token Index: 785

Text #8

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7429. Min Act: -0.1700

Data Index: 2445270 (Open Web Text)

Max Activating Token Index: 505

Text #9

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7298. Min Act: -0.1700

Data Index: 8444859 (Open Web Text)

Max Activating Token Index: 411

Text #10

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7341. Min Act: -0.1700

Data Index: 664139 (Open Web Text)

Max Activating Token Index: 632

Text #11

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7276. Min Act: -0.1700

Data Index: 7251061 (Open Web Text)

Max Activating Token Index: 423

Text #12

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6930. Min Act: -0.1700

Data Index: 7938038 (Open Web Text)

Max Activating Token Index: 471

Text #13

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7071. Min Act: -0.1700

Data Index: 4307637 (Open Web Text)

Max Activating Token Index: 629

Text #14

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7015. Min Act: -0.1700

Data Index: 4846028 (Open Web Text)

Max Activating Token Index: 558

Text #15

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6999. Min Act: -0.1700

Data Index: 2203450 (Open Web Text)

Max Activating Token Index: 577

Text #16

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.7040. Min Act: -0.1699

Data Index: 3193852 (Open Web Text)

Max Activating Token Index: 426

Text #17

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6445. Min Act: -0.1700

Data Index: 7026247 (Open Web Text)

Max Activating Token Index: 500

Text #18

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6835. Min Act: -0.1700

Data Index: 3237960 (Open Web Text)

Max Activating Token Index: 961

Text #19

Max Range: 1.8625. Min Range: -1.8625

Max Act: 1.6629. Min Act: -0.1700

Data Index: 7417219 (Open Web Text)

Max Activating Token Index: 986