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

Dataset: Open Web Text

Neuron 1982 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: 4.1741. Min Range: -4.1741

Max Act: 4.1741. Min Act: -0.1700

Data Index: 7071070 (Open Web Text)

Max Activating Token Index: 3

Text #1

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1068. Min Act: -0.1700

Data Index: 431107 (Open Web Text)

Max Activating Token Index: 3

Text #2

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1093. Min Act: -0.1700

Data Index: 8002125 (Open Web Text)

Max Activating Token Index: 5

Text #3

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1068. Min Act: -0.1700

Data Index: 3905948 (Open Web Text)

Max Activating Token Index: 3

Text #4

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.1323. Min Act: -0.1700

Data Index: 1493177 (Open Web Text)

Max Activating Token Index: 7

Text #5

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0778. Min Act: -0.1700

Data Index: 5988666 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0412. Min Act: -0.1700

Data Index: 6190412 (Open Web Text)

Max Activating Token Index: 5

Text #7

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0633. Min Act: -0.1700

Data Index: 3392861 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0538. Min Act: -0.1700

Data Index: 7735818 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0484. Min Act: -0.1700

Data Index: 5825421 (Open Web Text)

Max Activating Token Index: 14

Text #10

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0733. Min Act: -0.1700

Data Index: 5669657 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0643. Min Act: -0.1700

Data Index: 4064440 (Open Web Text)

Max Activating Token Index: 12

Text #12

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0197. Min Act: -0.1700

Data Index: 2488383 (Open Web Text)

Max Activating Token Index: 9

Text #13

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0150. Min Act: -0.1700

Data Index: 1953958 (Open Web Text)

Max Activating Token Index: 8

Text #14

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0424. Min Act: -0.1700

Data Index: 2823754 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0365. Min Act: -0.1700

Data Index: 7297481 (Open Web Text)

Max Activating Token Index: 3

Text #16

Max Range: 4.1741. Min Range: -4.1741

Max Act: 4.0254. Min Act: -0.1700

Data Index: 1762600 (Open Web Text)

Max Activating Token Index: 6

Text #17

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9920. Min Act: -0.1700

Data Index: 5554918 (Open Web Text)

Max Activating Token Index: 9

Text #18

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9892. Min Act: -0.1700

Data Index: 1305031 (Open Web Text)

Max Activating Token Index: 3

Text #19

Max Range: 4.1741. Min Range: -4.1741

Max Act: 3.9878. Min Act: -0.1700

Data Index: 8762534 (Open Web Text)

Max Activating Token Index: 5