Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3524 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.9798. Min Act: -0.1700
Data Index: 3459880 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.8235. Min Act: -0.1700
Data Index: 2909808 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.7923. Min Act: -0.1700
Data Index: 2477531 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.7610. Min Act: -0.1700
Data Index: 5524663 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.7610. Min Act: -0.1700
Data Index: 2344961 (Open Web Text)
Max Activating Token Index: 421
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.6360. Min Act: -0.1700
Data Index: 2003753 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.6360. Min Act: -0.1700
Data Index: 8244101 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.6048. Min Act: -0.1700
Data Index: 8672863 (Open Web Text)
Max Activating Token Index: 68
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.6048. Min Act: -0.1700
Data Index: 4484882 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5735. Min Act: -0.1700
Data Index: 8566995 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5735. Min Act: -0.1700
Data Index: 2887417 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5423. Min Act: -0.1700
Data Index: 3829184 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5423. Min Act: -0.1700
Data Index: 7576871 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5110. Min Act: -0.1700
Data Index: 187163 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5423. Min Act: -0.1700
Data Index: 5000008 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.5110. Min Act: -0.1700
Data Index: 1779765 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.4798. Min Act: -0.1700
Data Index: 565833 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.4798. Min Act: -0.1700
Data Index: 4472581 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.4798. Min Act: -0.1700
Data Index: 3936108 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9798. Min Range: -6.9798
Max Act: 6.4798. Min Act: -0.1700
Data Index: 5077830 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #19