Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3389 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.9775. Min Act: -0.1700
Data Index: 4408191 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.7587. Min Act: -0.1700
Data Index: 744865 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.7587. Min Act: -0.1700
Data Index: 2255114 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6962. Min Act: -0.1700
Data Index: 1847760 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6650. Min Act: -0.1700
Data Index: 6118686 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6650. Min Act: -0.1700
Data Index: 7938636 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6650. Min Act: -0.1700
Data Index: 3512146 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6650. Min Act: -0.1700
Data Index: 3162616 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6650. Min Act: -0.1700
Data Index: 4764793 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 6132342 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6337. Min Act: -0.1700
Data Index: 8480971 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6337. Min Act: -0.1700
Data Index: 3709309 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 2160452 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 4813469 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 223460 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 8367574 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 5944306 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.6025. Min Act: -0.1700
Data Index: 394886 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.5712. Min Act: -0.1700
Data Index: 5469872 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9775. Min Range: -5.9775
Max Act: 5.5400. Min Act: -0.1700
Data Index: 7401375 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #19