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

Dataset: Open Web Text

Neuron 1514 in Layer 4

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: 2.1264. Min Range: -2.1264

Max Act: 2.1155. Min Act: -0.1700

Data Index: 7610963 (Open Web Text)

Max Activating Token Index: 533

Text #1

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.1264. Min Act: -0.1700

Data Index: 4726327 (Open Web Text)

Max Activating Token Index: 581

Text #2

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.1054. Min Act: -0.1697

Data Index: 5632406 (Open Web Text)

Max Activating Token Index: 938

Text #3

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.0734. Min Act: -0.1700

Data Index: 2073507 (Open Web Text)

Max Activating Token Index: 547

Text #4

Max Range: 2.1264. Min Range: -2.1264

Max Act: 2.0168. Min Act: -0.1700

Data Index: 3838154 (Open Web Text)

Max Activating Token Index: 113

Text #5

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9710. Min Act: -0.1700

Data Index: 8313755 (Open Web Text)

Max Activating Token Index: 794

Text #6

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9760. Min Act: -0.1700

Data Index: 2156690 (Open Web Text)

Max Activating Token Index: 94

Text #7

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9424. Min Act: -0.1699

Data Index: 5327908 (Open Web Text)

Max Activating Token Index: 438

Text #8

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9610. Min Act: -0.1700

Data Index: 7570843 (Open Web Text)

Max Activating Token Index: 794

Text #9

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9634. Min Act: -0.1700

Data Index: 4691029 (Open Web Text)

Max Activating Token Index: 738

Text #10

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9352. Min Act: -0.1700

Data Index: 1181487 (Open Web Text)

Max Activating Token Index: 637

Text #11

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9293. Min Act: -0.1698

Data Index: 8239199 (Open Web Text)

Max Activating Token Index: 520

Text #12

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9205. Min Act: -0.1700

Data Index: 1695502 (Open Web Text)

Max Activating Token Index: 399

Text #13

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.9002. Min Act: -0.1700

Data Index: 2954245 (Open Web Text)

Max Activating Token Index: 663

Text #14

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8848. Min Act: -0.1700

Data Index: 6271208 (Open Web Text)

Max Activating Token Index: 971

Text #15

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8880. Min Act: -0.1700

Data Index: 828329 (Open Web Text)

Max Activating Token Index: 611

Text #16

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8836. Min Act: -0.1699

Data Index: 1986123 (Open Web Text)

Max Activating Token Index: 606

Text #17

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8911. Min Act: -0.1700

Data Index: 4864960 (Open Web Text)

Max Activating Token Index: 410

Text #18

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8273. Min Act: -0.1700

Data Index: 1368474 (Open Web Text)

Max Activating Token Index: 112

Text #19

Max Range: 2.1264. Min Range: -2.1264

Max Act: 1.8360. Min Act: -0.1700

Data Index: 5486765 (Open Web Text)

Max Activating Token Index: 189