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

Dataset: Open Web Text

Neuron 2384 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: 4.1775. Min Range: -4.1775

Max Act: 4.1775. Min Act: -0.1700

Data Index: 7658430 (Open Web Text)

Max Activating Token Index: 586

Text #1

Max Range: 4.1775. Min Range: -4.1775

Max Act: 4.0718. Min Act: -0.1700

Data Index: 4477190 (Open Web Text)

Max Activating Token Index: 448

Text #2

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.9245. Min Act: -0.1700

Data Index: 2798601 (Open Web Text)

Max Activating Token Index: 644

Text #3

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.9425. Min Act: -0.1700

Data Index: 3436946 (Open Web Text)

Max Activating Token Index: 466

Text #4

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.9380. Min Act: -0.1700

Data Index: 8696078 (Open Web Text)

Max Activating Token Index: 612

Text #5

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.9283. Min Act: -0.1700

Data Index: 6129929 (Open Web Text)

Max Activating Token Index: 404

Text #6

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.9229. Min Act: -0.1700

Data Index: 2130859 (Open Web Text)

Max Activating Token Index: 631

Text #7

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8977. Min Act: -0.1700

Data Index: 1572078 (Open Web Text)

Max Activating Token Index: 623

Text #8

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8658. Min Act: -0.1700

Data Index: 2035038 (Open Web Text)

Max Activating Token Index: 390

Text #9

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8726. Min Act: -0.1700

Data Index: 806440 (Open Web Text)

Max Activating Token Index: 628

Text #10

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8403. Min Act: -0.1700

Data Index: 4729 (Open Web Text)

Max Activating Token Index: 375

Text #11

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8270. Min Act: -0.1700

Data Index: 2709102 (Open Web Text)

Max Activating Token Index: 151

Text #12

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8595. Min Act: -0.1700

Data Index: 4764858 (Open Web Text)

Max Activating Token Index: 345

Text #13

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8417. Min Act: -0.1700

Data Index: 1262102 (Open Web Text)

Max Activating Token Index: 689

Text #14

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8601. Min Act: -0.1700

Data Index: 3700821 (Open Web Text)

Max Activating Token Index: 664

Text #15

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8429. Min Act: -0.1700

Data Index: 3286093 (Open Web Text)

Max Activating Token Index: 424

Text #16

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8152. Min Act: -0.1700

Data Index: 1511364 (Open Web Text)

Max Activating Token Index: 385

Text #17

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.7993. Min Act: -0.1700

Data Index: 48324 (Open Web Text)

Max Activating Token Index: 327

Text #18

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8272. Min Act: -0.1700

Data Index: 2829758 (Open Web Text)

Max Activating Token Index: 604

Text #19

Max Range: 4.1775. Min Range: -4.1775

Max Act: 3.8203. Min Act: -0.1700

Data Index: 1700713 (Open Web Text)

Max Activating Token Index: 675