Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5368 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.7509. Min Act: -0.1700
Data Index: 1726669 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.6884. Min Act: -0.1700
Data Index: 6023935 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.6884. Min Act: -0.1700
Data Index: 6359129 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.6572. Min Act: -0.1700
Data Index: 6004430 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.5634. Min Act: -0.1700
Data Index: 2621196 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.5634. Min Act: -0.1700
Data Index: 257340 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.5009. Min Act: -0.1700
Data Index: 5082961 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.5009. Min Act: -0.1700
Data Index: 4522035 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.4697. Min Act: -0.1700
Data Index: 4192811 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.4384. Min Act: -0.1700
Data Index: 7152350 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.4384. Min Act: -0.1700
Data Index: 5198382 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.4072. Min Act: -0.1700
Data Index: 8306688 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.4072. Min Act: -0.1700
Data Index: 7197036 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.3759. Min Act: -0.1700
Data Index: 8411719 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.3759. Min Act: -0.1700
Data Index: 3599105 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.3759. Min Act: -0.1700
Data Index: 6194026 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.3759. Min Act: -0.1700
Data Index: 6128079 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.3759. Min Act: -0.1700
Data Index: 2800341 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.3447. Min Act: -0.1700
Data Index: 8436145 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7509. Min Range: -5.7509
Max Act: 5.2822. Min Act: -0.1700
Data Index: 2759730 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #19