Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.1027. Min Act: -0.1700
Data Index: 4945708 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.1027. Min Act: -0.1700
Data Index: 786735 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.1027. Min Act: -0.1700
Data Index: 5765558 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.1027. Min Act: -0.1700
Data Index: 4882182 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.1027. Min Act: -0.1700
Data Index: 1049661 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0402. Min Act: -0.1700
Data Index: 4534555 (Open Web Text)
Max Activating Token Index: 391
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0402. Min Act: -0.1700
Data Index: 378085 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0714. Min Act: -0.1700
Data Index: 246672 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 7411166 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0089. Min Act: -0.1700
Data Index: 6826636 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 6581616 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0089. Min Act: -0.1700
Data Index: 5598793 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0089. Min Act: -0.1700
Data Index: 3281078 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 5972531 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1027. Min Range: -4.1027
Max Act: 4.0089. Min Act: -0.1700
Data Index: 5600692 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 2849223 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 1706541 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 6708563 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 2400678 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1027. Min Range: -4.1027
Max Act: 3.9776. Min Act: -0.1700
Data Index: 7065601 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #19