Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1877 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.8591. Min Act: -0.1700
Data Index: 3674096 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6716. Min Act: -0.1700
Data Index: 5605889 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6404. Min Act: -0.1700
Data Index: 1299916 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6716. Min Act: -0.1700
Data Index: 3704093 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6404. Min Act: -0.1700
Data Index: 6429363 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6091. Min Act: -0.1700
Data Index: 7183627 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6091. Min Act: -0.1700
Data Index: 465702 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.6091. Min Act: -0.1700
Data Index: 3095257 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.5466. Min Act: -0.1700
Data Index: 6553215 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4529. Min Act: -0.1700
Data Index: 7782981 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4529. Min Act: -0.1700
Data Index: 3291818 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4529. Min Act: -0.1700
Data Index: 2250851 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 3663991 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 3888872 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 4562842 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 6856466 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 4562843 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 7069074 (Open Web Text)
Max Activating Token Index: 154
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.3904. Min Act: -0.1700
Data Index: 6371894 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8591. Min Range: -6.8591
Max Act: 6.4216. Min Act: -0.1700
Data Index: 1092098 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #19