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

Dataset: Open Web Text

Neuron 1090 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: 4.0272. Min Range: -4.0272

Max Act: 4.0272. Min Act: -0.1700

Data Index: 4529566 (Open Web Text)

Max Activating Token Index: 411

Text #1

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.9843. Min Act: -0.1700

Data Index: 1658977 (Open Web Text)

Max Activating Token Index: 90

Text #2

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.9691. Min Act: -0.1700

Data Index: 1398149 (Open Web Text)

Max Activating Token Index: 156

Text #3

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.9230. Min Act: -0.1700

Data Index: 3680232 (Open Web Text)

Max Activating Token Index: 959

Text #4

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.9104. Min Act: -0.1700

Data Index: 4323131 (Open Web Text)

Max Activating Token Index: 308

Text #5

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8925. Min Act: -0.1700

Data Index: 6812025 (Open Web Text)

Max Activating Token Index: 556

Text #6

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8951. Min Act: -0.1700

Data Index: 3453371 (Open Web Text)

Max Activating Token Index: 406

Text #7

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8915. Min Act: -0.1700

Data Index: 1464513 (Open Web Text)

Max Activating Token Index: 529

Text #8

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8523. Min Act: -0.1700

Data Index: 1673401 (Open Web Text)

Max Activating Token Index: 545

Text #9

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8733. Min Act: -0.1700

Data Index: 1540934 (Open Web Text)

Max Activating Token Index: 413

Text #10

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8676. Min Act: -0.1700

Data Index: 3127989 (Open Web Text)

Max Activating Token Index: 197

Text #11

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8516. Min Act: -0.1700

Data Index: 5417888 (Open Web Text)

Max Activating Token Index: 651

Text #12

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8434. Min Act: -0.1700

Data Index: 4445211 (Open Web Text)

Max Activating Token Index: 452

Text #13

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8243. Min Act: -0.1700

Data Index: 3056460 (Open Web Text)

Max Activating Token Index: 948

Text #14

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8377. Min Act: -0.1700

Data Index: 1512194 (Open Web Text)

Max Activating Token Index: 245

Text #15

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8456. Min Act: -0.1700

Data Index: 2963542 (Open Web Text)

Max Activating Token Index: 394

Text #16

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8344. Min Act: -0.1700

Data Index: 1236003 (Open Web Text)

Max Activating Token Index: 1016

Text #17

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8215. Min Act: -0.1700

Data Index: 365607 (Open Web Text)

Max Activating Token Index: 444

Text #18

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8341. Min Act: -0.1700

Data Index: 799060 (Open Web Text)

Max Activating Token Index: 983

Text #19

Max Range: 4.0272. Min Range: -4.0272

Max Act: 3.8263. Min Act: -0.1700

Data Index: 3812973 (Open Web Text)

Max Activating Token Index: 598