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

Dataset: Open Web Text

Neuron 728 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: 3.7088. Min Range: -3.7088

Max Act: 3.7088. Min Act: -0.1700

Data Index: 203045 (Open Web Text)

Max Activating Token Index: 620

Text #1

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.6980. Min Act: -0.1700

Data Index: 1840381 (Open Web Text)

Max Activating Token Index: 774

Text #2

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.6115. Min Act: -0.1700

Data Index: 8782154 (Open Web Text)

Max Activating Token Index: 974

Text #3

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5723. Min Act: -0.1700

Data Index: 4919833 (Open Web Text)

Max Activating Token Index: 622

Text #4

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5490. Min Act: -0.1700

Data Index: 5713757 (Open Web Text)

Max Activating Token Index: 996

Text #5

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5805. Min Act: -0.1700

Data Index: 4660380 (Open Web Text)

Max Activating Token Index: 400

Text #6

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5806. Min Act: -0.1700

Data Index: 1943228 (Open Web Text)

Max Activating Token Index: 269

Text #7

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5960. Min Act: -0.1700

Data Index: 2100031 (Open Web Text)

Max Activating Token Index: 951

Text #8

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5690. Min Act: -0.1700

Data Index: 3038623 (Open Web Text)

Max Activating Token Index: 523

Text #9

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5473. Min Act: -0.1700

Data Index: 7428294 (Open Web Text)

Max Activating Token Index: 403

Text #10

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5504. Min Act: -0.1700

Data Index: 4035139 (Open Web Text)

Max Activating Token Index: 387

Text #11

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5436. Min Act: -0.1700

Data Index: 8359520 (Open Web Text)

Max Activating Token Index: 835

Text #12

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5380. Min Act: -0.1700

Data Index: 398567 (Open Web Text)

Max Activating Token Index: 354

Text #13

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5442. Min Act: -0.1700

Data Index: 2466673 (Open Web Text)

Max Activating Token Index: 460

Text #14

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5074. Min Act: -0.1700

Data Index: 3232702 (Open Web Text)

Max Activating Token Index: 622

Text #15

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.4984. Min Act: -0.1700

Data Index: 5293087 (Open Web Text)

Max Activating Token Index: 607

Text #16

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5059. Min Act: -0.1700

Data Index: 2083137 (Open Web Text)

Max Activating Token Index: 871

Text #17

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5037. Min Act: -0.1700

Data Index: 8431083 (Open Web Text)

Max Activating Token Index: 1012

Text #18

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5271. Min Act: -0.1700

Data Index: 3829080 (Open Web Text)

Max Activating Token Index: 704

Text #19

Max Range: 3.7088. Min Range: -3.7088

Max Act: 3.5038. Min Act: -0.1700

Data Index: 5567973 (Open Web Text)

Max Activating Token Index: 550