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

Dataset: Open Web Text

Neuron 1649 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: 2.6115. Min Range: -2.6115

Max Act: 2.6115. Min Act: -0.1700

Data Index: 3414644 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5801. Min Act: -0.1700

Data Index: 4205789 (Open Web Text)

Max Activating Token Index: 18

Text #2

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5704. Min Act: -0.1700

Data Index: 5207216 (Open Web Text)

Max Activating Token Index: 8

Text #3

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5812. Min Act: -0.1700

Data Index: 8197995 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5798. Min Act: -0.1700

Data Index: 1170940 (Open Web Text)

Max Activating Token Index: 5

Text #5

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5682. Min Act: -0.1700

Data Index: 6530608 (Open Web Text)

Max Activating Token Index: 18

Text #6

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5580. Min Act: -0.1700

Data Index: 5531242 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5584. Min Act: -0.1700

Data Index: 5974675 (Open Web Text)

Max Activating Token Index: 12

Text #8

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5516. Min Act: -0.1700

Data Index: 6758032 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5518. Min Act: -0.1700

Data Index: 6883890 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5536. Min Act: -0.1700

Data Index: 7315838 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5559. Min Act: -0.1700

Data Index: 2425588 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5351. Min Act: -0.1700

Data Index: 3505597 (Open Web Text)

Max Activating Token Index: 7

Text #13

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5437. Min Act: -0.1700

Data Index: 190320 (Open Web Text)

Max Activating Token Index: 13

Text #14

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5373. Min Act: -0.1700

Data Index: 5428342 (Open Web Text)

Max Activating Token Index: 13

Text #15

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5397. Min Act: -0.1700

Data Index: 5215359 (Open Web Text)

Max Activating Token Index: 8

Text #16

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5380. Min Act: -0.1700

Data Index: 7967561 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5424. Min Act: -0.1700

Data Index: 2420299 (Open Web Text)

Max Activating Token Index: 3

Text #18

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5449. Min Act: -0.1700

Data Index: 4539910 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 2.6115. Min Range: -2.6115

Max Act: 2.5402. Min Act: -0.1700

Data Index: 4812347 (Open Web Text)

Max Activating Token Index: 4