Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.7947. Min Act: -0.1700
Data Index: 680706 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.3572. Min Act: -0.1700
Data Index: 8108366 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.3572. Min Act: -0.1700
Data Index: 2770499 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.2947. Min Act: -0.1700
Data Index: 8158526 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.2322. Min Act: -0.1700
Data Index: 4400117 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.2322. Min Act: -0.1700
Data Index: 7049030 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.2322. Min Act: -0.1700
Data Index: 5541250 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.1697. Min Act: -0.1700
Data Index: 716698 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.1697. Min Act: -0.1700
Data Index: 6409196 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.1697. Min Act: -0.1700
Data Index: 3277229 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.1697. Min Act: -0.1700
Data Index: 7188814 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.1697. Min Act: -0.1700
Data Index: 8019118 (Open Web Text)
Max Activating Token Index: 324
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.1072. Min Act: -0.1700
Data Index: 1601747 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.0447. Min Act: -0.1700
Data Index: 3165735 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.0447. Min Act: -0.1700
Data Index: 5393159 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7947. Min Range: -8.7947
Max Act: 8.0447. Min Act: -0.1700
Data Index: 4937850 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7947. Min Range: -8.7947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 76773 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7947. Min Range: -8.7947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 349613 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7947. Min Range: -8.7947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 7558348 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7947. Min Range: -8.7947
Max Act: 7.9822. Min Act: -0.1700
Data Index: 6373056 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #19