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

Dataset: Open Web Text

Neuron 2996 in Layer 2

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: 1.7218. Min Range: -1.7218

Max Act: 1.7218. Min Act: -0.1700

Data Index: 6598491 (Open Web Text)

Max Activating Token Index: 329

Text #1

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7111. Min Act: -0.1700

Data Index: 3345584 (Open Web Text)

Max Activating Token Index: 8

Text #2

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7001. Min Act: -0.1700

Data Index: 2837481 (Open Web Text)

Max Activating Token Index: 16

Text #3

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7000. Min Act: -0.1700

Data Index: 4039267 (Open Web Text)

Max Activating Token Index: 6

Text #4

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6959. Min Act: -0.1700

Data Index: 6826287 (Open Web Text)

Max Activating Token Index: 13

Text #5

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.7018. Min Act: -0.1700

Data Index: 8020041 (Open Web Text)

Max Activating Token Index: 6

Text #6

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6840. Min Act: -0.1700

Data Index: 3104933 (Open Web Text)

Max Activating Token Index: 4

Text #7

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6788. Min Act: -0.1699

Data Index: 6015193 (Open Web Text)

Max Activating Token Index: 6

Text #8

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6758. Min Act: -0.1700

Data Index: 5075874 (Open Web Text)

Max Activating Token Index: 6

Text #9

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6801. Min Act: -0.1700

Data Index: 7789159 (Open Web Text)

Max Activating Token Index: 7

Text #10

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6696. Min Act: -0.1700

Data Index: 7733452 (Open Web Text)

Max Activating Token Index: 247

Text #11

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6669. Min Act: -0.1700

Data Index: 759162 (Open Web Text)

Max Activating Token Index: 8

Text #12

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6662. Min Act: -0.1700

Data Index: 175960 (Open Web Text)

Max Activating Token Index: 467

Text #13

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6496. Min Act: -0.1700

Data Index: 8771063 (Open Web Text)

Max Activating Token Index: 446

Text #14

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6637. Min Act: -0.1700

Data Index: 2537897 (Open Web Text)

Max Activating Token Index: 16

Text #15

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6535. Min Act: -0.1700

Data Index: 1388345 (Open Web Text)

Max Activating Token Index: 11

Text #16

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6483. Min Act: -0.1700

Data Index: 3212119 (Open Web Text)

Max Activating Token Index: 5

Text #17

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6582. Min Act: -0.1700

Data Index: 3629275 (Open Web Text)

Max Activating Token Index: 8

Text #18

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6536. Min Act: -0.1700

Data Index: 4965987 (Open Web Text)

Max Activating Token Index: 4

Text #19

Max Range: 1.7218. Min Range: -1.7218

Max Act: 1.6680. Min Act: -0.1700

Data Index: 8410820 (Open Web Text)

Max Activating Token Index: 731