Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2801 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1650. Min Range: -8.1650
Max Act: 8.1650. Min Act: -0.1700
Data Index: 8329624 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1650. Min Range: -8.1650
Max Act: 8.0400. Min Act: -0.1700
Data Index: 7509661 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.9150. Min Act: -0.1700
Data Index: 8226865 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.9775. Min Act: -0.1700
Data Index: 6768035 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.9775. Min Act: -0.1700
Data Index: 3622886 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.9150. Min Act: -0.1700
Data Index: 7691519 (Open Web Text)
Max Activating Token Index: 558
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.8525. Min Act: -0.1700
Data Index: 6031462 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.8525. Min Act: -0.1700
Data Index: 479722 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.8525. Min Act: -0.1700
Data Index: 2712591 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.8525. Min Act: -0.1700
Data Index: 2552752 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.7900. Min Act: -0.1700
Data Index: 1024302 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.7900. Min Act: -0.1700
Data Index: 3426870 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.7275. Min Act: -0.1700
Data Index: 8468842 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.6962. Min Act: -0.1700
Data Index: 5404442 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.7275. Min Act: -0.1700
Data Index: 1273571 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.6962. Min Act: -0.1700
Data Index: 8609155 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.6962. Min Act: -0.1700
Data Index: 218065 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.6650. Min Act: -0.1700
Data Index: 1012702 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.6025. Min Act: -0.1700
Data Index: 2192497 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1650. Min Range: -8.1650
Max Act: 7.6337. Min Act: -0.1700
Data Index: 5428375 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #19