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

Dataset: Open Web Text

Neuron 1464 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: 3.0224. Min Range: -3.0224

Max Act: 3.0224. Min Act: -0.1700

Data Index: 8648059 (Open Web Text)

Max Activating Token Index: 481

Text #1

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9573. Min Act: -0.1700

Data Index: 4463738 (Open Web Text)

Max Activating Token Index: 76

Text #2

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9833. Min Act: -0.1700

Data Index: 5364333 (Open Web Text)

Max Activating Token Index: 956

Text #3

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9236. Min Act: -0.1700

Data Index: 1824820 (Open Web Text)

Max Activating Token Index: 304

Text #4

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9347. Min Act: -0.1700

Data Index: 5895098 (Open Web Text)

Max Activating Token Index: 954

Text #5

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8359. Min Act: -0.1700

Data Index: 7373147 (Open Web Text)

Max Activating Token Index: 622

Text #6

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.9291. Min Act: -0.1700

Data Index: 2306347 (Open Web Text)

Max Activating Token Index: 980

Text #7

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8665. Min Act: -0.1700

Data Index: 7630612 (Open Web Text)

Max Activating Token Index: 350

Text #8

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8157. Min Act: -0.1700

Data Index: 5615116 (Open Web Text)

Max Activating Token Index: 670

Text #9

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.8427. Min Act: -0.1700

Data Index: 2010787 (Open Web Text)

Max Activating Token Index: 960

Text #10

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7978. Min Act: -0.1700

Data Index: 1135050 (Open Web Text)

Max Activating Token Index: 1010

Text #11

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7772. Min Act: -0.1700

Data Index: 8354330 (Open Web Text)

Max Activating Token Index: 1003

Text #12

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7809. Min Act: -0.1700

Data Index: 287851 (Open Web Text)

Max Activating Token Index: 897

Text #13

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7757. Min Act: -0.1700

Data Index: 5871443 (Open Web Text)

Max Activating Token Index: 574

Text #14

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7535. Min Act: -0.1700

Data Index: 6364985 (Open Web Text)

Max Activating Token Index: 840

Text #15

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7573. Min Act: -0.1700

Data Index: 6245176 (Open Web Text)

Max Activating Token Index: 600

Text #16

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7589. Min Act: -0.1700

Data Index: 989001 (Open Web Text)

Max Activating Token Index: 88

Text #17

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7658. Min Act: -0.1700

Data Index: 200896 (Open Web Text)

Max Activating Token Index: 590

Text #18

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7378. Min Act: -0.1700

Data Index: 2294210 (Open Web Text)

Max Activating Token Index: 710

Text #19

Max Range: 3.0224. Min Range: -3.0224

Max Act: 2.7733. Min Act: -0.1700

Data Index: 7794017 (Open Web Text)

Max Activating Token Index: 874