Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5745 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6478. Min Range: -8.6478
Max Act: 8.6478. Min Act: -0.1700
Data Index: 3110049 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6478. Min Range: -8.6478
Max Act: 8.5228. Min Act: -0.1700
Data Index: 291929 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6478. Min Range: -8.6478
Max Act: 8.3978. Min Act: -0.1700
Data Index: 3043656 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6478. Min Range: -8.6478
Max Act: 8.2103. Min Act: -0.1700
Data Index: 3569982 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6478. Min Range: -8.6478
Max Act: 8.1478. Min Act: -0.1700
Data Index: 1060820 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6478. Min Range: -8.6478
Max Act: 8.0853. Min Act: -0.1700
Data Index: 386842 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.8665. Min Act: -0.1700
Data Index: 1743867 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.8353. Min Act: -0.1700
Data Index: 2551277 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.8040. Min Act: -0.1700
Data Index: 1630679 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.8040. Min Act: -0.1700
Data Index: 2157184 (Open Web Text)
Max Activating Token Index: 176
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.8040. Min Act: -0.1700
Data Index: 8321011 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.8040. Min Act: -0.1700
Data Index: 1541552 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7728. Min Act: -0.1700
Data Index: 3672208 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7415. Min Act: -0.1700
Data Index: 5648691 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7415. Min Act: -0.1700
Data Index: 855257 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7415. Min Act: -0.1700
Data Index: 3103599 (Open Web Text)
Max Activating Token Index: 182
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7103. Min Act: -0.1700
Data Index: 4346164 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7103. Min Act: -0.1700
Data Index: 7737046 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.7103. Min Act: -0.1700
Data Index: 5551624 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6478. Min Range: -8.6478
Max Act: 7.6790. Min Act: -0.1700
Data Index: 6923494 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19