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

Dataset: Open Web Text

Neuron 163 in Layer 1

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: 4.4221. Min Range: -4.4221

Max Act: 4.4221. Min Act: -0.1700

Data Index: 691736 (Open Web Text)

Max Activating Token Index: 866

Text #1

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.3660. Min Act: -0.1700

Data Index: 7297306 (Open Web Text)

Max Activating Token Index: 130

Text #2

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1828. Min Act: -0.1700

Data Index: 4514666 (Open Web Text)

Max Activating Token Index: 116

Text #3

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.2309. Min Act: -0.1700

Data Index: 2312200 (Open Web Text)

Max Activating Token Index: 817

Text #4

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1724. Min Act: -0.1700

Data Index: 8650181 (Open Web Text)

Max Activating Token Index: 607

Text #5

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1912. Min Act: -0.1700

Data Index: 7912238 (Open Web Text)

Max Activating Token Index: 140

Text #6

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1624. Min Act: -0.1700

Data Index: 5214047 (Open Web Text)

Max Activating Token Index: 685

Text #7

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1616. Min Act: -0.1700

Data Index: 5330084 (Open Web Text)

Max Activating Token Index: 478

Text #8

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1564. Min Act: -0.1700

Data Index: 8345878 (Open Web Text)

Max Activating Token Index: 459

Text #9

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1346. Min Act: -0.1700

Data Index: 8434327 (Open Web Text)

Max Activating Token Index: 482

Text #10

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1308. Min Act: -0.1700

Data Index: 7800358 (Open Web Text)

Max Activating Token Index: 781

Text #11

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1275. Min Act: -0.1700

Data Index: 2666404 (Open Web Text)

Max Activating Token Index: 295

Text #12

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1437. Min Act: -0.1700

Data Index: 7627078 (Open Web Text)

Max Activating Token Index: 543

Text #13

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1416. Min Act: -0.1700

Data Index: 4788069 (Open Web Text)

Max Activating Token Index: 185

Text #14

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.1012. Min Act: -0.1700

Data Index: 3638608 (Open Web Text)

Max Activating Token Index: 752

Text #15

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.0390. Min Act: -0.1700

Data Index: 5330087 (Open Web Text)

Max Activating Token Index: 638

Text #16

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.0883. Min Act: -0.1700

Data Index: 6261410 (Open Web Text)

Max Activating Token Index: 651

Text #17

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.0857. Min Act: -0.1700

Data Index: 375787 (Open Web Text)

Max Activating Token Index: 804

Text #18

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.0530. Min Act: -0.1700

Data Index: 5822532 (Open Web Text)

Max Activating Token Index: 381

Text #19

Max Range: 4.4221. Min Range: -4.4221

Max Act: 4.0562. Min Act: -0.1700

Data Index: 5032544 (Open Web Text)

Max Activating Token Index: 137