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

Dataset: Open Web Text

Neuron 1004 in Layer 0

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: 5.1665. Min Range: -5.1665

Max Act: 5.1665. Min Act: -0.1700

Data Index: 1500829 (Open Web Text)

Max Activating Token Index: 4

Text #1

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.1315. Min Act: -0.1700

Data Index: 7614118 (Open Web Text)

Max Activating Token Index: 4

Text #2

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.1042. Min Act: -0.1700

Data Index: 1436663 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0383. Min Act: -0.1700

Data Index: 6610877 (Open Web Text)

Max Activating Token Index: 5

Text #4

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0332. Min Act: -0.1700

Data Index: 634399 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0390. Min Act: -0.1700

Data Index: 6084139 (Open Web Text)

Max Activating Token Index: 4

Text #6

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0394. Min Act: -0.1700

Data Index: 1215419 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0371. Min Act: -0.1700

Data Index: 7279139 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0105. Min Act: -0.1700

Data Index: 3135412 (Open Web Text)

Max Activating Token Index: 2

Text #9

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0105. Min Act: -0.1700

Data Index: 2026485 (Open Web Text)

Max Activating Token Index: 2

Text #10

Max Range: 5.1665. Min Range: -5.1665

Max Act: 5.0105. Min Act: -0.1700

Data Index: 8690887 (Open Web Text)

Max Activating Token Index: 2

Text #11

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9717. Min Act: -0.1700

Data Index: 545034 (Open Web Text)

Max Activating Token Index: 5

Text #12

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9824. Min Act: -0.1700

Data Index: 1545568 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9842. Min Act: -0.1700

Data Index: 6985704 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9779. Min Act: -0.1700

Data Index: 8474677 (Open Web Text)

Max Activating Token Index: 3

Text #15

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9388. Min Act: -0.1700

Data Index: 5625805 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9470. Min Act: -0.1700

Data Index: 2979285 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9410. Min Act: -0.1700

Data Index: 1747828 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9410. Min Act: -0.1700

Data Index: 5880394 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 5.1665. Min Range: -5.1665

Max Act: 4.9410. Min Act: -0.1700

Data Index: 3716565 (Open Web Text)

Max Activating Token Index: 3