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

Dataset: Open Web Text

Neuron 1569 in Layer 6

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: 3.3065. Min Range: -3.3065

Max Act: 3.2955. Min Act: -0.1700

Data Index: 735741 (Open Web Text)

Max Activating Token Index: 552

Text #1

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.3065. Min Act: -0.1700

Data Index: 1187409 (Open Web Text)

Max Activating Token Index: 197

Text #2

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2809. Min Act: -0.1700

Data Index: 6369614 (Open Web Text)

Max Activating Token Index: 828

Text #3

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2658. Min Act: -0.1700

Data Index: 6014175 (Open Web Text)

Max Activating Token Index: 258

Text #4

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2552. Min Act: -0.1700

Data Index: 3317271 (Open Web Text)

Max Activating Token Index: 235

Text #5

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2644. Min Act: -0.1700

Data Index: 3994387 (Open Web Text)

Max Activating Token Index: 379

Text #6

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2268. Min Act: -0.1700

Data Index: 6608546 (Open Web Text)

Max Activating Token Index: 653

Text #7

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2290. Min Act: -0.1700

Data Index: 5199802 (Open Web Text)

Max Activating Token Index: 768

Text #8

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2248. Min Act: -0.1700

Data Index: 5401036 (Open Web Text)

Max Activating Token Index: 270

Text #9

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2195. Min Act: -0.1700

Data Index: 2146705 (Open Web Text)

Max Activating Token Index: 857

Text #10

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1976. Min Act: -0.1700

Data Index: 1302967 (Open Web Text)

Max Activating Token Index: 448

Text #11

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2187. Min Act: -0.1700

Data Index: 7723575 (Open Web Text)

Max Activating Token Index: 392

Text #12

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2077. Min Act: -0.1700

Data Index: 3850687 (Open Web Text)

Max Activating Token Index: 996

Text #13

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.2003. Min Act: -0.1700

Data Index: 4764492 (Open Web Text)

Max Activating Token Index: 886

Text #14

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1843. Min Act: -0.1700

Data Index: 3606499 (Open Web Text)

Max Activating Token Index: 678

Text #15

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1754. Min Act: -0.1700

Data Index: 6234568 (Open Web Text)

Max Activating Token Index: 722

Text #16

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1776. Min Act: -0.1700

Data Index: 7569606 (Open Web Text)

Max Activating Token Index: 595

Text #17

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1667. Min Act: -0.1700

Data Index: 5040046 (Open Web Text)

Max Activating Token Index: 575

Text #18

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1702. Min Act: -0.1700

Data Index: 2061378 (Open Web Text)

Max Activating Token Index: 437

Text #19

Max Range: 3.3065. Min Range: -3.3065

Max Act: 3.1678. Min Act: -0.1700

Data Index: 50957 (Open Web Text)

Max Activating Token Index: 1000