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

Dataset: Open Web Text

Neuron 2089 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: 4.7812. Min Range: -4.7812

Max Act: 4.7812. Min Act: -0.1700

Data Index: 7383729 (Open Web Text)

Max Activating Token Index: 5

Text #1

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7563. Min Act: -0.1700

Data Index: 2095459 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7492. Min Act: -0.1700

Data Index: 2093019 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7408. Min Act: -0.1700

Data Index: 562118 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7353. Min Act: -0.1700

Data Index: 2312634 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7381. Min Act: -0.1700

Data Index: 343867 (Open Web Text)

Max Activating Token Index: 5

Text #6

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7060. Min Act: -0.1700

Data Index: 881991 (Open Web Text)

Max Activating Token Index: 9

Text #7

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7013. Min Act: -0.1700

Data Index: 1671662 (Open Web Text)

Max Activating Token Index: 10

Text #8

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7111. Min Act: -0.1700

Data Index: 5049289 (Open Web Text)

Max Activating Token Index: 9

Text #9

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.7167. Min Act: -0.1700

Data Index: 1563638 (Open Web Text)

Max Activating Token Index: 8

Text #10

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6839. Min Act: -0.1700

Data Index: 5905970 (Open Web Text)

Max Activating Token Index: 8

Text #11

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6903. Min Act: -0.1700

Data Index: 6097188 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6865. Min Act: -0.1700

Data Index: 6744910 (Open Web Text)

Max Activating Token Index: 4

Text #13

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6988. Min Act: -0.1700

Data Index: 8144530 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6659. Min Act: -0.1700

Data Index: 8562236 (Open Web Text)

Max Activating Token Index: 6

Text #15

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6953. Min Act: -0.1700

Data Index: 961106 (Open Web Text)

Max Activating Token Index: 4

Text #16

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6844. Min Act: -0.1700

Data Index: 1880385 (Open Web Text)

Max Activating Token Index: 7

Text #17

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6803. Min Act: -0.1700

Data Index: 3645757 (Open Web Text)

Max Activating Token Index: 4

Text #18

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6371. Min Act: -0.1699

Data Index: 1241461 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.7812. Min Range: -4.7812

Max Act: 4.6565. Min Act: -0.1700

Data Index: 2731533 (Open Web Text)

Max Activating Token Index: 4