Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2502 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.9150. Min Act: -0.1700
Data Index: 2796848 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.7588. Min Act: -0.1700
Data Index: 2272027 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.4463. Min Act: -0.1700
Data Index: 7506575 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.4150. Min Act: -0.1700
Data Index: 6319016 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.3838. Min Act: -0.1700
Data Index: 910990 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.3525. Min Act: -0.1700
Data Index: 1812466 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.3525. Min Act: -0.1700
Data Index: 4124439 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.2900. Min Act: -0.1700
Data Index: 7079713 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.2588. Min Act: -0.1700
Data Index: 6431317 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.2588. Min Act: -0.1700
Data Index: 2741560 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1963. Min Act: -0.1700
Data Index: 2414857 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1963. Min Act: -0.1700
Data Index: 5677042 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1963. Min Act: -0.1700
Data Index: 967019 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1963. Min Act: -0.1700
Data Index: 101617 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1338. Min Act: -0.1700
Data Index: 3422156 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1338. Min Act: -0.1700
Data Index: 8501833 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.1025. Min Act: -0.1700
Data Index: 2345411 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.0713. Min Act: -0.1700
Data Index: 6428925 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.0400. Min Act: -0.1700
Data Index: 1022260 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9150. Min Range: -6.9150
Max Act: 6.0400. Min Act: -0.1700
Data Index: 4432711 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #19