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

Dataset: Open Web Text

Neuron 219 in Layer 5

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: 4.6872. Min Range: -4.6872

Max Act: 4.6872. Min Act: -0.1700

Data Index: 4880790 (Open Web Text)

Max Activating Token Index: 204

Text #1

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6580. Min Act: -0.1700

Data Index: 85267 (Open Web Text)

Max Activating Token Index: 649

Text #2

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6112. Min Act: -0.1700

Data Index: 6892303 (Open Web Text)

Max Activating Token Index: 531

Text #3

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.6003. Min Act: -0.1700

Data Index: 2556837 (Open Web Text)

Max Activating Token Index: 408

Text #4

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5881. Min Act: -0.1700

Data Index: 5724041 (Open Web Text)

Max Activating Token Index: 858

Text #5

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5861. Min Act: -0.1700

Data Index: 4098305 (Open Web Text)

Max Activating Token Index: 1012

Text #6

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5894. Min Act: -0.1700

Data Index: 1312247 (Open Web Text)

Max Activating Token Index: 891

Text #7

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5424. Min Act: -0.1700

Data Index: 5998423 (Open Web Text)

Max Activating Token Index: 694

Text #8

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5299. Min Act: -0.1700

Data Index: 1374147 (Open Web Text)

Max Activating Token Index: 719

Text #9

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.5465. Min Act: -0.1700

Data Index: 6115498 (Open Web Text)

Max Activating Token Index: 939

Text #10

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4798. Min Act: -0.1700

Data Index: 7689123 (Open Web Text)

Max Activating Token Index: 621

Text #11

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4911. Min Act: -0.1700

Data Index: 3333077 (Open Web Text)

Max Activating Token Index: 766

Text #12

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4707. Min Act: -0.1700

Data Index: 5204643 (Open Web Text)

Max Activating Token Index: 787

Text #13

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4902. Min Act: -0.1700

Data Index: 7967364 (Open Web Text)

Max Activating Token Index: 130

Text #14

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4846. Min Act: -0.1700

Data Index: 3558813 (Open Web Text)

Max Activating Token Index: 554

Text #15

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4681. Min Act: -0.1700

Data Index: 5963169 (Open Web Text)

Max Activating Token Index: 777

Text #16

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4621. Min Act: -0.1700

Data Index: 5059615 (Open Web Text)

Max Activating Token Index: 777

Text #17

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4244. Min Act: -0.1700

Data Index: 119350 (Open Web Text)

Max Activating Token Index: 916

Text #18

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4287. Min Act: -0.1700

Data Index: 4638402 (Open Web Text)

Max Activating Token Index: 875

Text #19

Max Range: 4.6872. Min Range: -4.6872

Max Act: 4.4632. Min Act: -0.1700

Data Index: 183152 (Open Web Text)

Max Activating Token Index: 231