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

Dataset: Open Web Text

Neuron 760 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: 4.2426. Min Range: -4.2426

Max Act: 4.2426. Min Act: -0.1700

Data Index: 2673981 (Open Web Text)

Max Activating Token Index: 881

Text #1

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.2060. Min Act: -0.1700

Data Index: 7576132 (Open Web Text)

Max Activating Token Index: 904

Text #2

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.2158. Min Act: -0.1700

Data Index: 5688070 (Open Web Text)

Max Activating Token Index: 756

Text #3

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.2073. Min Act: -0.1700

Data Index: 4738446 (Open Web Text)

Max Activating Token Index: 286

Text #4

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1763. Min Act: -0.1700

Data Index: 2334670 (Open Web Text)

Max Activating Token Index: 593

Text #5

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1529. Min Act: -0.1700

Data Index: 3361466 (Open Web Text)

Max Activating Token Index: 957

Text #6

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1284. Min Act: -0.1700

Data Index: 1541423 (Open Web Text)

Max Activating Token Index: 547

Text #7

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1508. Min Act: -0.1700

Data Index: 843413 (Open Web Text)

Max Activating Token Index: 601

Text #8

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1602. Min Act: -0.1700

Data Index: 7026563 (Open Web Text)

Max Activating Token Index: 911

Text #9

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1423. Min Act: -0.1700

Data Index: 1631920 (Open Web Text)

Max Activating Token Index: 499

Text #10

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1571. Min Act: -0.1700

Data Index: 3262690 (Open Web Text)

Max Activating Token Index: 888

Text #11

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1804. Min Act: -0.1700

Data Index: 8034566 (Open Web Text)

Max Activating Token Index: 950

Text #12

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1199. Min Act: -0.1700

Data Index: 1202518 (Open Web Text)

Max Activating Token Index: 605

Text #13

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1208. Min Act: -0.1700

Data Index: 6985578 (Open Web Text)

Max Activating Token Index: 519

Text #14

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1240. Min Act: -0.1700

Data Index: 1282515 (Open Web Text)

Max Activating Token Index: 926

Text #15

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.0875. Min Act: -0.1700

Data Index: 1219354 (Open Web Text)

Max Activating Token Index: 915

Text #16

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1339. Min Act: -0.1700

Data Index: 278340 (Open Web Text)

Max Activating Token Index: 873

Text #17

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1000. Min Act: -0.1700

Data Index: 3948347 (Open Web Text)

Max Activating Token Index: 536

Text #18

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1267. Min Act: -0.1700

Data Index: 3194081 (Open Web Text)

Max Activating Token Index: 853

Text #19

Max Range: 4.2426. Min Range: -4.2426

Max Act: 4.1041. Min Act: -0.1700

Data Index: 5387477 (Open Web Text)

Max Activating Token Index: 972