Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6384 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.2492. Min Act: -0.1700
Data Index: 3820158 (Open Web Text)
Max Activating Token Index: 487
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.1242. Min Act: -0.1700
Data Index: 5345539 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.2492. Min Range: -5.2492
Max Act: 5.0617. Min Act: -0.1700
Data Index: 6750054 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 8003871 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 4509266 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 4197881 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9992. Min Act: -0.1700
Data Index: 5470447 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 6222712 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 314385 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.9055. Min Act: -0.1700
Data Index: 291175 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 2319757 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 3693063 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 1392117 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8742. Min Act: -0.1700
Data Index: 2813 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 4188009 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8742. Min Act: -0.1700
Data Index: 4153973 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 59942 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 2168371 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 1834133 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.2492. Min Range: -5.2492
Max Act: 4.8430. Min Act: -0.1700
Data Index: 2756881 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #19