Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3376 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.8783. Min Act: -0.1700
Data Index: 173812 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.8783. Min Act: -0.1700
Data Index: 6968598 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.7846. Min Act: -0.1700
Data Index: 8171930 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.7533. Min Act: -0.1700
Data Index: 1875431 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.7221. Min Act: -0.1700
Data Index: 8121539 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6908. Min Act: -0.1700
Data Index: 3011682 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6908. Min Act: -0.1700
Data Index: 2943637 (Open Web Text)
Max Activating Token Index: 854
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6908. Min Act: -0.1700
Data Index: 238257 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6908. Min Act: -0.1700
Data Index: 7656697 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6596. Min Act: -0.1700
Data Index: 7472277 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6596. Min Act: -0.1700
Data Index: 5881310 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6596. Min Act: -0.1700
Data Index: 736123 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6283. Min Act: -0.1700
Data Index: 6560423 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.6283. Min Act: -0.1700
Data Index: 3342763 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5971. Min Act: -0.1700
Data Index: 678320 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5783273 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5035524 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5971. Min Act: -0.1700
Data Index: 8630545 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5971. Min Act: -0.1700
Data Index: 5353014 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8783. Min Range: -5.8783
Max Act: 5.5346. Min Act: -0.1700
Data Index: 6879760 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #19