Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1182 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8878. Min Range: -8.8878
Max Act: 8.8878. Min Act: -0.1700
Data Index: 291714 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8878. Min Range: -8.8878
Max Act: 8.6378. Min Act: -0.1700
Data Index: 2252886 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8878. Min Range: -8.8878
Max Act: 8.0128. Min Act: -0.1700
Data Index: 7280698 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8878. Min Range: -8.8878
Max Act: 8.0128. Min Act: -0.1700
Data Index: 7625275 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.8878. Min Act: -0.1700
Data Index: 3783254 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.7003. Min Act: -0.1700
Data Index: 7687336 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.7003. Min Act: -0.1700
Data Index: 4302524 (Open Web Text)
Max Activating Token Index: 71
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.7003. Min Act: -0.1700
Data Index: 1986675 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.5753. Min Act: -0.1700
Data Index: 4537583 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.5753. Min Act: -0.1700
Data Index: 7350030 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.5128. Min Act: -0.1700
Data Index: 3936039 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4815. Min Act: -0.1700
Data Index: 4158091 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4815. Min Act: -0.1700
Data Index: 2077662 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4815. Min Act: -0.1700
Data Index: 5675497 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4815. Min Act: -0.1700
Data Index: 7231992 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4503. Min Act: -0.1700
Data Index: 7479441 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4503. Min Act: -0.1700
Data Index: 8501938 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4190. Min Act: -0.1700
Data Index: 3116985 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.4190. Min Act: -0.1700
Data Index: 8331309 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8878. Min Range: -8.8878
Max Act: 7.3878. Min Act: -0.1700
Data Index: 5981240 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #19