Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3358 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0688. Min Range: -7.0688
Max Act: 7.0688. Min Act: -0.1700
Data Index: 4556347 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.8501. Min Act: -0.1700
Data Index: 7289357 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.5063. Min Act: -0.1700
Data Index: 1902649 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.4438. Min Act: -0.1700
Data Index: 5388202 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.2876. Min Act: -0.1700
Data Index: 7171186 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.2563. Min Act: -0.1700
Data Index: 408534 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.2563. Min Act: -0.1700
Data Index: 156469 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.1938. Min Act: -0.1700
Data Index: 6081855 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.1626. Min Act: -0.1700
Data Index: 1341486 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.0688. Min Act: -0.1700
Data Index: 2128605 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0688. Min Range: -7.0688
Max Act: 6.0063. Min Act: -0.1700
Data Index: 8338617 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9751. Min Act: -0.1700
Data Index: 1572823 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9438. Min Act: -0.1700
Data Index: 2764659 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9438. Min Act: -0.1700
Data Index: 5377192 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9751. Min Act: -0.1700
Data Index: 2231742 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9751. Min Act: -0.1700
Data Index: 5557851 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9126. Min Act: -0.1700
Data Index: 4845129 (Open Web Text)
Max Activating Token Index: 147
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9438. Min Act: -0.1700
Data Index: 1649660 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.9126. Min Act: -0.1700
Data Index: 688338 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0688. Min Range: -7.0688
Max Act: 5.8813. Min Act: -0.1700
Data Index: 655408 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #19