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

Dataset: Open Web Text

Neuron 106 in Layer 3

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: 3.2390. Min Range: -3.2390

Max Act: 3.2390. Min Act: -0.1700

Data Index: 3323342 (Open Web Text)

Max Activating Token Index: 39

Text #1

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.2072. Min Act: -0.1700

Data Index: 4961853 (Open Web Text)

Max Activating Token Index: 917

Text #2

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1954. Min Act: -0.1700

Data Index: 8073526 (Open Web Text)

Max Activating Token Index: 130

Text #3

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1839. Min Act: -0.1700

Data Index: 8073525 (Open Web Text)

Max Activating Token Index: 78

Text #4

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.2025. Min Act: -0.1700

Data Index: 97340 (Open Web Text)

Max Activating Token Index: 439

Text #5

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1762. Min Act: -0.1700

Data Index: 416166 (Open Web Text)

Max Activating Token Index: 466

Text #6

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1720. Min Act: -0.1700

Data Index: 6522956 (Open Web Text)

Max Activating Token Index: 13

Text #7

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1630. Min Act: -0.1700

Data Index: 3816390 (Open Web Text)

Max Activating Token Index: 2

Text #8

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1630. Min Act: -0.1700

Data Index: 8629141 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1630. Min Act: -0.1700

Data Index: 1271861 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1630. Min Act: -0.1700

Data Index: 3808792 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1630. Min Act: -0.1700

Data Index: 6255608 (Open Web Text)

Max Activating Token Index: 2

Text #12

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1395. Min Act: -0.1700

Data Index: 5284432 (Open Web Text)

Max Activating Token Index: 360

Text #13

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1631. Min Act: -0.1700

Data Index: 2801734 (Open Web Text)

Max Activating Token Index: 823

Text #14

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1191. Min Act: -0.1700

Data Index: 493474 (Open Web Text)

Max Activating Token Index: 439

Text #15

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1252. Min Act: -0.1700

Data Index: 22954 (Open Web Text)

Max Activating Token Index: 524

Text #16

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1320. Min Act: -0.1700

Data Index: 1098873 (Open Web Text)

Max Activating Token Index: 563

Text #17

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1185. Min Act: -0.1700

Data Index: 211129 (Open Web Text)

Max Activating Token Index: 485

Text #18

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1096. Min Act: -0.1700

Data Index: 2068015 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.2390. Min Range: -3.2390

Max Act: 3.1223. Min Act: -0.1700

Data Index: 3288560 (Open Web Text)

Max Activating Token Index: 59