Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5270 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.8884. Min Act: -0.1700
Data Index: 8629666 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.5759. Min Act: -0.1700
Data Index: 7937154 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.5759. Min Act: -0.1700
Data Index: 2130814 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.5134. Min Act: -0.1700
Data Index: 5232689 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3884. Min Act: -0.1700
Data Index: 5211405 (Open Web Text)
Max Activating Token Index: 93
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3884. Min Act: -0.1700
Data Index: 3044029 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3259. Min Act: -0.1700
Data Index: 898567 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3884. Min Act: -0.1700
Data Index: 5065040 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3884. Min Act: -0.1700
Data Index: 2687891 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3259. Min Act: -0.1700
Data Index: 8098056 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3259. Min Act: -0.1700
Data Index: 4661849 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.3259. Min Act: -0.1700
Data Index: 323605 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2634. Min Act: -0.1700
Data Index: 360685 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2634. Min Act: -0.1700
Data Index: 2857103 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2009. Min Act: -0.1700
Data Index: 2015884 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2009. Min Act: -0.1700
Data Index: 7142174 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2009. Min Act: -0.1700
Data Index: 7385847 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2009. Min Act: -0.1700
Data Index: 4135623 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2009. Min Act: -0.1700
Data Index: 5202384 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.8884. Min Range: -10.8884
Max Act: 10.2009. Min Act: -0.1700
Data Index: 898566 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #19