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

Dataset: Open Web Text

Neuron 947 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: 4.7709. Min Range: -4.7709

Max Act: 4.7709. Min Act: -0.1700

Data Index: 5262484 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7663. Min Act: -0.1700

Data Index: 1026727 (Open Web Text)

Max Activating Token Index: 9

Text #2

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7556. Min Act: -0.1700

Data Index: 51263 (Open Web Text)

Max Activating Token Index: 4

Text #3

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7452. Min Act: -0.1700

Data Index: 4364574 (Open Web Text)

Max Activating Token Index: 4

Text #4

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7259. Min Act: -0.1700

Data Index: 739890 (Open Web Text)

Max Activating Token Index: 10

Text #5

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7263. Min Act: -0.1700

Data Index: 8683159 (Open Web Text)

Max Activating Token Index: 7

Text #6

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7391. Min Act: -0.1700

Data Index: 2783628 (Open Web Text)

Max Activating Token Index: 83

Text #7

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7126. Min Act: -0.1700

Data Index: 2066804 (Open Web Text)

Max Activating Token Index: 5

Text #8

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7218. Min Act: -0.1700

Data Index: 4517819 (Open Web Text)

Max Activating Token Index: 14

Text #9

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7344. Min Act: -0.1700

Data Index: 1395035 (Open Web Text)

Max Activating Token Index: 5

Text #10

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6885. Min Act: -0.1700

Data Index: 1110221 (Open Web Text)

Max Activating Token Index: 6

Text #11

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.7010. Min Act: -0.1700

Data Index: 1582337 (Open Web Text)

Max Activating Token Index: 10

Text #12

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6485. Min Act: -0.1700

Data Index: 4937488 (Open Web Text)

Max Activating Token Index: 6

Text #13

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6777. Min Act: -0.1700

Data Index: 5657935 (Open Web Text)

Max Activating Token Index: 4

Text #14

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6525. Min Act: -0.1700

Data Index: 6110298 (Open Web Text)

Max Activating Token Index: 8

Text #15

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6716. Min Act: -0.1700

Data Index: 6347368 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6680. Min Act: -0.1700

Data Index: 2432980 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6543. Min Act: -0.1700

Data Index: 6505975 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6828. Min Act: -0.1700

Data Index: 6601205 (Open Web Text)

Max Activating Token Index: 6

Text #19

Max Range: 4.7709. Min Range: -4.7709

Max Act: 4.6594. Min Act: -0.1700

Data Index: 7220773 (Open Web Text)

Max Activating Token Index: 4