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

Dataset: Open Web Text

Neuron 1431 in Layer 2

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: 1.1995. Min Range: -1.1995

Max Act: 1.1995. Min Act: -0.1700

Data Index: 2137419 (Open Web Text)

Max Activating Token Index: 307

Text #1

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1915. Min Act: -0.1699

Data Index: 1153923 (Open Web Text)

Max Activating Token Index: 277

Text #2

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1823. Min Act: -0.1699

Data Index: 3165137 (Open Web Text)

Max Activating Token Index: 277

Text #3

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1784. Min Act: -0.1700

Data Index: 3165151 (Open Web Text)

Max Activating Token Index: 261

Text #4

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1797. Min Act: -0.1678

Data Index: 966357 (Open Web Text)

Max Activating Token Index: 300

Text #5

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1737. Min Act: -0.1700

Data Index: 3165136 (Open Web Text)

Max Activating Token Index: 284

Text #6

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1654. Min Act: -0.1696

Data Index: 3165140 (Open Web Text)

Max Activating Token Index: 328

Text #7

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1657. Min Act: -0.1700

Data Index: 1153954 (Open Web Text)

Max Activating Token Index: 314

Text #8

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1523. Min Act: -0.1700

Data Index: 3165154 (Open Web Text)

Max Activating Token Index: 288

Text #9

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1594. Min Act: -0.1607

Data Index: 3165150 (Open Web Text)

Max Activating Token Index: 278

Text #10

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1653. Min Act: -0.1699

Data Index: 7540752 (Open Web Text)

Max Activating Token Index: 237

Text #11

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1454. Min Act: -0.1679

Data Index: 3165153 (Open Web Text)

Max Activating Token Index: 311

Text #12

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1552. Min Act: -0.1700

Data Index: 2137430 (Open Web Text)

Max Activating Token Index: 278

Text #13

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1358. Min Act: -0.1700

Data Index: 7011862 (Open Web Text)

Max Activating Token Index: 324

Text #14

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1149. Min Act: -0.1698

Data Index: 966365 (Open Web Text)

Max Activating Token Index: 291

Text #15

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1322. Min Act: -0.1700

Data Index: 1153930 (Open Web Text)

Max Activating Token Index: 312

Text #16

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1218. Min Act: -0.1697

Data Index: 5193202 (Open Web Text)

Max Activating Token Index: 321

Text #17

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1323. Min Act: -0.1700

Data Index: 1153928 (Open Web Text)

Max Activating Token Index: 303

Text #18

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1134. Min Act: -0.1700

Data Index: 487493 (Open Web Text)

Max Activating Token Index: 326

Text #19

Max Range: 1.1995. Min Range: -1.1995

Max Act: 1.1133. Min Act: -0.1700

Data Index: 3165149 (Open Web Text)

Max Activating Token Index: 307