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

Dataset: Open Web Text

Neuron 150 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: 7.0421. Min Range: -7.0421

Max Act: 7.0183. Min Act: -0.1700

Data Index: 1359481 (Open Web Text)

Max Activating Token Index: 948

Text #1

Max Range: 7.0421. Min Range: -7.0421

Max Act: 7.0421. Min Act: -0.1700

Data Index: 7599473 (Open Web Text)

Max Activating Token Index: 497

Text #2

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.8554. Min Act: -0.1700

Data Index: 4493372 (Open Web Text)

Max Activating Token Index: 202

Text #3

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.8384. Min Act: -0.1700

Data Index: 6961998 (Open Web Text)

Max Activating Token Index: 769

Text #4

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.7820. Min Act: -0.1700

Data Index: 6236816 (Open Web Text)

Max Activating Token Index: 338

Text #5

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.7727. Min Act: -0.1700

Data Index: 5858656 (Open Web Text)

Max Activating Token Index: 978

Text #6

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.7808. Min Act: -0.1700

Data Index: 6236817 (Open Web Text)

Max Activating Token Index: 248

Text #7

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.6773. Min Act: -0.1700

Data Index: 4280743 (Open Web Text)

Max Activating Token Index: 146

Text #8

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.5776. Min Act: -0.1700

Data Index: 864232 (Open Web Text)

Max Activating Token Index: 735

Text #9

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.5199. Min Act: -0.1700

Data Index: 6519103 (Open Web Text)

Max Activating Token Index: 197

Text #10

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.6373. Min Act: -0.1700

Data Index: 3156153 (Open Web Text)

Max Activating Token Index: 360

Text #11

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.4381. Min Act: -0.1700

Data Index: 6024168 (Open Web Text)

Max Activating Token Index: 905

Text #12

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.4462. Min Act: -0.1700

Data Index: 1442901 (Open Web Text)

Max Activating Token Index: 1012

Text #13

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.5908. Min Act: -0.1700

Data Index: 4692959 (Open Web Text)

Max Activating Token Index: 720

Text #14

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.5279. Min Act: -0.1700

Data Index: 6006989 (Open Web Text)

Max Activating Token Index: 361

Text #15

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.5435. Min Act: -0.1700

Data Index: 5476868 (Open Web Text)

Max Activating Token Index: 838

Text #16

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.6098. Min Act: -0.1700

Data Index: 4183145 (Open Web Text)

Max Activating Token Index: 24

Text #17

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.6124. Min Act: -0.1700

Data Index: 2513511 (Open Web Text)

Max Activating Token Index: 537

Text #18

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.4837. Min Act: -0.1700

Data Index: 1829949 (Open Web Text)

Max Activating Token Index: 248

Text #19

Max Range: 7.0421. Min Range: -7.0421

Max Act: 6.4396. Min Act: -0.1700

Data Index: 6057273 (Open Web Text)

Max Activating Token Index: 860