Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6062 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0978. Min Range: -5.0978
Max Act: 5.0978. Min Act: -0.1700
Data Index: 7595386 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0978. Min Range: -5.0978
Max Act: 5.0353. Min Act: -0.1700
Data Index: 2510889 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.9415. Min Act: -0.1700
Data Index: 8392012 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.9415. Min Act: -0.1700
Data Index: 7293801 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.8790. Min Act: -0.1700
Data Index: 6983 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.8478. Min Act: -0.1700
Data Index: 4379134 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.8478. Min Act: -0.1700
Data Index: 2555430 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.8165. Min Act: -0.1700
Data Index: 1947515 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.8165. Min Act: -0.1700
Data Index: 4334851 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.8165. Min Act: -0.1700
Data Index: 5001036 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 3616920 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7853. Min Act: -0.1700
Data Index: 3038433 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7853. Min Act: -0.1700
Data Index: 7852405 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7853. Min Act: -0.1700
Data Index: 619872 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7853. Min Act: -0.1700
Data Index: 5452507 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 347234 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 5445746 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 396719 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 7126600 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0978. Min Range: -5.0978
Max Act: 4.7540. Min Act: -0.1700
Data Index: 7389403 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #19