Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2968 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5584. Min Range: -7.5584
Max Act: 7.5584. Min Act: -0.1700
Data Index: 3990087 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.6209. Min Act: -0.1700
Data Index: 1475812 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.5271. Min Act: -0.1700
Data Index: 6899663 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.5271. Min Act: -0.1700
Data Index: 5733807 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.4021. Min Act: -0.1700
Data Index: 3051898 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.3709. Min Act: -0.1700
Data Index: 4048619 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.3396. Min Act: -0.1700
Data Index: 7866799 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.2771. Min Act: -0.1700
Data Index: 6879372 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.2771. Min Act: -0.1700
Data Index: 6705592 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.2146. Min Act: -0.1700
Data Index: 5521614 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.1521. Min Act: -0.1700
Data Index: 3215218 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.1209. Min Act: -0.1700
Data Index: 1454349 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0896. Min Act: -0.1700
Data Index: 1475819 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0896. Min Act: -0.1700
Data Index: 3065957 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0896. Min Act: -0.1700
Data Index: 6879385 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0584. Min Act: -0.1700
Data Index: 6903610 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0584. Min Act: -0.1700
Data Index: 874833 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0271. Min Act: -0.1700
Data Index: 6347010 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0584. Min Act: -0.1700
Data Index: 5691841 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5584. Min Range: -7.5584
Max Act: 6.0271. Min Act: -0.1700
Data Index: 1475821 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #19