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

Dataset: Open Web Text

Neuron 1240 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: 5.7421. Min Range: -5.7421

Max Act: 5.7421. Min Act: -0.1700

Data Index: 2371908 (Open Web Text)

Max Activating Token Index: 12

Text #1

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.6529. Min Act: -0.1550

Data Index: 236250 (Open Web Text)

Max Activating Token Index: 15

Text #2

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.6004. Min Act: -0.1678

Data Index: 236251 (Open Web Text)

Max Activating Token Index: 14

Text #3

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.6154. Min Act: -0.1700

Data Index: 96656 (Open Web Text)

Max Activating Token Index: 12

Text #4

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.5741. Min Act: -0.1669

Data Index: 7271395 (Open Web Text)

Max Activating Token Index: 14

Text #5

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.5235. Min Act: -0.1700

Data Index: 1897096 (Open Web Text)

Max Activating Token Index: 12

Text #6

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.4962. Min Act: -0.1700

Data Index: 1739763 (Open Web Text)

Max Activating Token Index: 11

Text #7

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.4820. Min Act: -0.1699

Data Index: 5517020 (Open Web Text)

Max Activating Token Index: 17

Text #8

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.4700. Min Act: -0.1700

Data Index: 6434514 (Open Web Text)

Max Activating Token Index: 13

Text #9

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.4351. Min Act: -0.1700

Data Index: 7841424 (Open Web Text)

Max Activating Token Index: 11

Text #10

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.4410. Min Act: -0.1700

Data Index: 7841425 (Open Web Text)

Max Activating Token Index: 12

Text #11

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.4050. Min Act: -0.1700

Data Index: 7841429 (Open Web Text)

Max Activating Token Index: 11

Text #12

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3797. Min Act: -0.1700

Data Index: 1054554 (Open Web Text)

Max Activating Token Index: 48

Text #13

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3903. Min Act: -0.1700

Data Index: 2825463 (Open Web Text)

Max Activating Token Index: 11

Text #14

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3663. Min Act: -0.1700

Data Index: 5517005 (Open Web Text)

Max Activating Token Index: 10

Text #15

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3680. Min Act: -0.1700

Data Index: 3644182 (Open Web Text)

Max Activating Token Index: 14

Text #16

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3611. Min Act: -0.1631

Data Index: 236247 (Open Web Text)

Max Activating Token Index: 223

Text #17

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3672. Min Act: -0.1699

Data Index: 1054559 (Open Web Text)

Max Activating Token Index: 13

Text #18

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3659. Min Act: -0.1700

Data Index: 5122303 (Open Web Text)

Max Activating Token Index: 11

Text #19

Max Range: 5.7421. Min Range: -5.7421

Max Act: 5.3284. Min Act: -0.1700

Data Index: 5517019 (Open Web Text)

Max Activating Token Index: 10