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

Dataset: Open Web Text

Neuron 1992 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: 7.0616. Min Range: -7.0616

Max Act: 7.0460. Min Act: -0.1700

Data Index: 5144686 (Open Web Text)

Max Activating Token Index: 9

Text #1

Max Range: 7.0616. Min Range: -7.0616

Max Act: 7.0616. Min Act: -0.1700

Data Index: 5974929 (Open Web Text)

Max Activating Token Index: 6

Text #2

Max Range: 7.0616. Min Range: -7.0616

Max Act: 7.0605. Min Act: -0.1700

Data Index: 1861594 (Open Web Text)

Max Activating Token Index: 6

Text #3

Max Range: 7.0616. Min Range: -7.0616

Max Act: 7.0297. Min Act: -0.1700

Data Index: 1038886 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 7.0616. Min Range: -7.0616

Max Act: 7.0182. Min Act: -0.1700

Data Index: 3908755 (Open Web Text)

Max Activating Token Index: 6

Text #5

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9435. Min Act: -0.1700

Data Index: 1820467 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9667. Min Act: -0.1700

Data Index: 8229471 (Open Web Text)

Max Activating Token Index: 6

Text #7

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9729. Min Act: -0.1700

Data Index: 470539 (Open Web Text)

Max Activating Token Index: 4

Text #8

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.8907. Min Act: -0.1700

Data Index: 1006466 (Open Web Text)

Max Activating Token Index: 4

Text #9

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9328. Min Act: -0.1700

Data Index: 6156865 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9236. Min Act: -0.1700

Data Index: 6015857 (Open Web Text)

Max Activating Token Index: 4

Text #11

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9033. Min Act: -0.1700

Data Index: 6246512 (Open Web Text)

Max Activating Token Index: 4

Text #12

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9049. Min Act: -0.1700

Data Index: 1424985 (Open Web Text)

Max Activating Token Index: 5

Text #13

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.8815. Min Act: -0.1700

Data Index: 1595911 (Open Web Text)

Max Activating Token Index: 6

Text #14

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.8882. Min Act: -0.1700

Data Index: 4781622 (Open Web Text)

Max Activating Token Index: 4

Text #15

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.8773. Min Act: -0.1700

Data Index: 8783704 (Open Web Text)

Max Activating Token Index: 6

Text #16

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9130. Min Act: -0.1700

Data Index: 783654 (Open Web Text)

Max Activating Token Index: 4

Text #17

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.8826. Min Act: -0.1700

Data Index: 2079603 (Open Web Text)

Max Activating Token Index: 6

Text #18

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.8979. Min Act: -0.1700

Data Index: 1745181 (Open Web Text)

Max Activating Token Index: 7

Text #19

Max Range: 7.0616. Min Range: -7.0616

Max Act: 6.9290. Min Act: -0.1699

Data Index: 8803718 (Open Web Text)

Max Activating Token Index: 7