Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4710 in Layer 30
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.9048. Min Act: -0.1700
Data Index: 1831955 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.8735. Min Act: -0.1700
Data Index: 4378709 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.8423. Min Act: -0.1700
Data Index: 7868457 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.7173. Min Act: -0.1700
Data Index: 7195726 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.7173. Min Act: -0.1700
Data Index: 2801412 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.7173. Min Act: -0.1700
Data Index: 830169 (Open Web Text)
Max Activating Token Index: 48
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.6860. Min Act: -0.1700
Data Index: 238853 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.6860. Min Act: -0.1700
Data Index: 3896093 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.6860. Min Act: -0.1700
Data Index: 6223309 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 7954378 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 6643401 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 712675 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 8548771 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 3597128 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 1582907 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 2099659 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5923. Min Act: -0.1700
Data Index: 8560010 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5610. Min Act: -0.1700
Data Index: 344250 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5610. Min Act: -0.1700
Data Index: 36208 (Open Web Text)
Max Activating Token Index: 316
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9048. Min Range: -5.9048
Max Act: 5.5610. Min Act: -0.1700
Data Index: 2809855 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19