Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 648 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.9058. Min Act: -0.1700
Data Index: 8277506 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8433. Min Act: -0.1700
Data Index: 4927944 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8433. Min Act: -0.1700
Data Index: 721633 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8433. Min Act: -0.1700
Data Index: 6789420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1700
Data Index: 2081941 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1693
Data Index: 60809 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1691
Data Index: 60810 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1699
Data Index: 2027611 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1698
Data Index: 1442902 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1700
Data Index: 1037112 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1700
Data Index: 1209398 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1700
Data Index: 3174979 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1700
Data Index: 3463882 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.8120. Min Act: -0.1700
Data Index: 7028328 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.7808. Min Act: -0.1700
Data Index: 8027708 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.7808. Min Act: -0.1700
Data Index: 5621960 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.7495. Min Act: -0.1699
Data Index: 6976702 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.7495. Min Act: -0.1700
Data Index: 7496552 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.7183. Min Act: -0.1700
Data Index: 2579605 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9058. Min Range: -4.9058
Max Act: 4.7183. Min Act: -0.1700
Data Index: 6130108 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19