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

Dataset: Open Web Text

Neuron 2253 in Layer 0

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: 1.8010. Min Range: -1.8010

Max Act: 1.8010. Min Act: -0.0942

Data Index: 898658 (Open Web Text)

Max Activating Token Index: 282

Text #1

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7570. Min Act: -0.0903

Data Index: 5896026 (Open Web Text)

Max Activating Token Index: 79

Text #2

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7552. Min Act: -0.1063

Data Index: 2076610 (Open Web Text)

Max Activating Token Index: 57

Text #3

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7366. Min Act: -0.0521

Data Index: 7033918 (Open Web Text)

Max Activating Token Index: 481

Text #4

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7387. Min Act: -0.1480

Data Index: 902940 (Open Web Text)

Max Activating Token Index: 884

Text #5

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7289. Min Act: -0.1319

Data Index: 5669452 (Open Web Text)

Max Activating Token Index: 30

Text #6

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7234. Min Act: -0.1262

Data Index: 6849407 (Open Web Text)

Max Activating Token Index: 64

Text #7

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7125. Min Act: -0.1377

Data Index: 1813331 (Open Web Text)

Max Activating Token Index: 283

Text #8

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7152. Min Act: -0.1413

Data Index: 6849409 (Open Web Text)

Max Activating Token Index: 470

Text #9

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7204. Min Act: -0.1700

Data Index: 3589305 (Open Web Text)

Max Activating Token Index: 754

Text #10

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7219. Min Act: -0.1559

Data Index: 6584978 (Open Web Text)

Max Activating Token Index: 676

Text #11

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7163. Min Act: -0.1536

Data Index: 8669125 (Open Web Text)

Max Activating Token Index: 15

Text #12

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7067. Min Act: -0.1699

Data Index: 440895 (Open Web Text)

Max Activating Token Index: 840

Text #13

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7083. Min Act: -0.1142

Data Index: 6762417 (Open Web Text)

Max Activating Token Index: 531

Text #14

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7033. Min Act: -0.1416

Data Index: 5301637 (Open Web Text)

Max Activating Token Index: 870

Text #15

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7015. Min Act: -0.1313

Data Index: 762721 (Open Web Text)

Max Activating Token Index: 907

Text #16

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6976. Min Act: -0.1381

Data Index: 6186120 (Open Web Text)

Max Activating Token Index: 503

Text #17

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.7032. Min Act: -0.1245

Data Index: 7626341 (Open Web Text)

Max Activating Token Index: 413

Text #18

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6916. Min Act: -0.1585

Data Index: 5345973 (Open Web Text)

Max Activating Token Index: 842

Text #19

Max Range: 1.8010. Min Range: -1.8010

Max Act: 1.6820. Min Act: -0.1365

Data Index: 5592090 (Open Web Text)

Max Activating Token Index: 744