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

Dataset: Open Web Text

Neuron 1203 in Layer 1

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: 1.6525. Min Range: -1.6525

Max Act: 1.6525. Min Act: -0.1700

Data Index: 1801197 (Open Web Text)

Max Activating Token Index: 152

Text #1

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.6302. Min Act: -0.1700

Data Index: 697870 (Open Web Text)

Max Activating Token Index: 361

Text #2

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.6093. Min Act: -0.1700

Data Index: 1801196 (Open Web Text)

Max Activating Token Index: 59

Text #3

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.6074. Min Act: -0.1700

Data Index: 3739942 (Open Web Text)

Max Activating Token Index: 601

Text #4

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.6067. Min Act: -0.1700

Data Index: 4807481 (Open Web Text)

Max Activating Token Index: 533

Text #5

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5980. Min Act: -0.1700

Data Index: 6872586 (Open Web Text)

Max Activating Token Index: 621

Text #6

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5909. Min Act: -0.1700

Data Index: 3471704 (Open Web Text)

Max Activating Token Index: 70

Text #7

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5885. Min Act: -0.1700

Data Index: 1377379 (Open Web Text)

Max Activating Token Index: 451

Text #8

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5832. Min Act: -0.1700

Data Index: 8533902 (Open Web Text)

Max Activating Token Index: 502

Text #9

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5829. Min Act: -0.1700

Data Index: 2375075 (Open Web Text)

Max Activating Token Index: 192

Text #10

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5785. Min Act: -0.1700

Data Index: 6859475 (Open Web Text)

Max Activating Token Index: 854

Text #11

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5759. Min Act: -0.1700

Data Index: 5687950 (Open Web Text)

Max Activating Token Index: 120

Text #12

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5707. Min Act: -0.1700

Data Index: 6940941 (Open Web Text)

Max Activating Token Index: 321

Text #13

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5739. Min Act: -0.1700

Data Index: 1362789 (Open Web Text)

Max Activating Token Index: 596

Text #14

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5628. Min Act: -0.1700

Data Index: 6815158 (Open Web Text)

Max Activating Token Index: 533

Text #15

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5630. Min Act: -0.1700

Data Index: 2488851 (Open Web Text)

Max Activating Token Index: 419

Text #16

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5653. Min Act: -0.1700

Data Index: 4942691 (Open Web Text)

Max Activating Token Index: 207

Text #17

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5571. Min Act: -0.1698

Data Index: 3637879 (Open Web Text)

Max Activating Token Index: 375

Text #18

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5505. Min Act: -0.1699

Data Index: 4981346 (Open Web Text)

Max Activating Token Index: 301

Text #19

Max Range: 1.6525. Min Range: -1.6525

Max Act: 1.5526. Min Act: -0.1700

Data Index: 1487068 (Open Web Text)

Max Activating Token Index: 280