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

Dataset: Open Web Text

Neuron 1173 in Layer 5

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: 4.1932. Min Range: -4.1932

Max Act: 4.1932. Min Act: -0.1700

Data Index: 1982187 (Open Web Text)

Max Activating Token Index: 574

Text #1

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1895. Min Act: -0.1700

Data Index: 7073359 (Open Web Text)

Max Activating Token Index: 149

Text #2

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1665. Min Act: -0.1700

Data Index: 567441 (Open Web Text)

Max Activating Token Index: 773

Text #3

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1389. Min Act: -0.1700

Data Index: 4121477 (Open Web Text)

Max Activating Token Index: 654

Text #4

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1315. Min Act: -0.1700

Data Index: 6469400 (Open Web Text)

Max Activating Token Index: 810

Text #5

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1657. Min Act: -0.1700

Data Index: 63220 (Open Web Text)

Max Activating Token Index: 402

Text #6

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1344. Min Act: -0.1700

Data Index: 148279 (Open Web Text)

Max Activating Token Index: 564

Text #7

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1500. Min Act: -0.1700

Data Index: 7594567 (Open Web Text)

Max Activating Token Index: 961

Text #8

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.0975. Min Act: -0.1700

Data Index: 3082977 (Open Web Text)

Max Activating Token Index: 701

Text #9

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1121. Min Act: -0.1700

Data Index: 1049071 (Open Web Text)

Max Activating Token Index: 406

Text #10

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1048. Min Act: -0.1700

Data Index: 8049339 (Open Web Text)

Max Activating Token Index: 285

Text #11

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.0900. Min Act: -0.1700

Data Index: 2864903 (Open Web Text)

Max Activating Token Index: 677

Text #12

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1062. Min Act: -0.1700

Data Index: 653477 (Open Web Text)

Max Activating Token Index: 241

Text #13

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1365. Min Act: -0.1700

Data Index: 7392643 (Open Web Text)

Max Activating Token Index: 649

Text #14

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1039. Min Act: -0.1700

Data Index: 3233960 (Open Web Text)

Max Activating Token Index: 942

Text #15

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.1097. Min Act: -0.1700

Data Index: 5090566 (Open Web Text)

Max Activating Token Index: 451

Text #16

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.0466. Min Act: -0.1700

Data Index: 773875 (Open Web Text)

Max Activating Token Index: 103

Text #17

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.0522. Min Act: -0.1700

Data Index: 1429154 (Open Web Text)

Max Activating Token Index: 240

Text #18

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.0984. Min Act: -0.1700

Data Index: 2911413 (Open Web Text)

Max Activating Token Index: 969

Text #19

Max Range: 4.1932. Min Range: -4.1932

Max Act: 4.0851. Min Act: -0.1700

Data Index: 2952358 (Open Web Text)

Max Activating Token Index: 231