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

Dataset: Open Web Text

Neuron 980 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: 4.1832. Min Range: -4.1832

Max Act: 4.1635. Min Act: -0.1700

Data Index: 7265214 (Open Web Text)

Max Activating Token Index: 567

Text #1

Max Range: 4.1832. Min Range: -4.1832

Max Act: 4.1832. Min Act: -0.1700

Data Index: 726276 (Open Web Text)

Max Activating Token Index: 383

Text #2

Max Range: 4.1832. Min Range: -4.1832

Max Act: 4.1342. Min Act: -0.1700

Data Index: 4145181 (Open Web Text)

Max Activating Token Index: 135

Text #3

Max Range: 4.1832. Min Range: -4.1832

Max Act: 4.1217. Min Act: -0.1700

Data Index: 4153330 (Open Web Text)

Max Activating Token Index: 363

Text #4

Max Range: 4.1832. Min Range: -4.1832

Max Act: 4.0884. Min Act: -0.1700

Data Index: 1690524 (Open Web Text)

Max Activating Token Index: 509

Text #5

Max Range: 4.1832. Min Range: -4.1832

Max Act: 4.0474. Min Act: -0.1700

Data Index: 7426631 (Open Web Text)

Max Activating Token Index: 605

Text #6

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.9894. Min Act: -0.1700

Data Index: 6232346 (Open Web Text)

Max Activating Token Index: 75

Text #7

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.9311. Min Act: -0.1700

Data Index: 3606461 (Open Web Text)

Max Activating Token Index: 984

Text #8

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.8885. Min Act: -0.1700

Data Index: 2702441 (Open Web Text)

Max Activating Token Index: 319

Text #9

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.9100. Min Act: -0.1700

Data Index: 4965048 (Open Web Text)

Max Activating Token Index: 464

Text #10

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.8429. Min Act: -0.1700

Data Index: 2120898 (Open Web Text)

Max Activating Token Index: 838

Text #11

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.8916. Min Act: -0.1700

Data Index: 125394 (Open Web Text)

Max Activating Token Index: 813

Text #12

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.8386. Min Act: -0.1700

Data Index: 1789932 (Open Web Text)

Max Activating Token Index: 583

Text #13

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7924. Min Act: -0.1700

Data Index: 8675299 (Open Web Text)

Max Activating Token Index: 314

Text #14

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7721. Min Act: -0.1699

Data Index: 8624546 (Open Web Text)

Max Activating Token Index: 102

Text #15

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7963. Min Act: -0.1700

Data Index: 1260372 (Open Web Text)

Max Activating Token Index: 742

Text #16

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7764. Min Act: -0.1700

Data Index: 519773 (Open Web Text)

Max Activating Token Index: 608

Text #17

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7655. Min Act: -0.1700

Data Index: 3683188 (Open Web Text)

Max Activating Token Index: 838

Text #18

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7967. Min Act: -0.1700

Data Index: 1703337 (Open Web Text)

Max Activating Token Index: 895

Text #19

Max Range: 4.1832. Min Range: -4.1832

Max Act: 3.7441. Min Act: -0.1700

Data Index: 8364794 (Open Web Text)

Max Activating Token Index: 597