Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2778 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.5815. Min Act: -0.1700
Data Index: 65996 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.0190. Min Act: -0.1700
Data Index: 829320 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5815. Min Range: -7.5815
Max Act: 7.0190. Min Act: -0.1700
Data Index: 5834221 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.9878. Min Act: -0.1700
Data Index: 5367799 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8940. Min Act: -0.1700
Data Index: 6635122 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8940. Min Act: -0.1700
Data Index: 2215244 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8315. Min Act: -0.1700
Data Index: 4368789 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8315. Min Act: -0.1700
Data Index: 363910 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7690. Min Act: -0.1700
Data Index: 300540 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8003. Min Act: -0.1700
Data Index: 5278872 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8315. Min Act: -0.1700
Data Index: 3419455 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8003. Min Act: -0.1700
Data Index: 4749341 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.8003. Min Act: -0.1700
Data Index: 198854 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7378. Min Act: -0.1700
Data Index: 5460463 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7690. Min Act: -0.1700
Data Index: 4781200 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7690. Min Act: -0.1700
Data Index: 7446677 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7065. Min Act: -0.1700
Data Index: 3156398 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7378. Min Act: -0.1700
Data Index: 1706952 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7065. Min Act: -0.1700
Data Index: 27005 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5815. Min Range: -7.5815
Max Act: 6.7065. Min Act: -0.1700
Data Index: 3391350 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #19