Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3115 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0720. Min Range: -8.0720
Max Act: 8.0720. Min Act: -0.1700
Data Index: 7552962 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.9782. Min Act: -0.1700
Data Index: 4418625 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.8845. Min Act: -0.1700
Data Index: 1812500 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.8220. Min Act: -0.1700
Data Index: 1480649 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.7595. Min Act: -0.1700
Data Index: 5452377 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.7282. Min Act: -0.1700
Data Index: 4420646 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6970. Min Act: -0.1700
Data Index: 6784769 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6970. Min Act: -0.1700
Data Index: 3304178 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6657. Min Act: -0.1700
Data Index: 1366667 (Open Web Text)
Max Activating Token Index: 323
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6345. Min Act: -0.1700
Data Index: 2034142 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6345. Min Act: -0.1700
Data Index: 1275442 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6345. Min Act: -0.1700
Data Index: 4465828 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6032. Min Act: -0.1700
Data Index: 7866662 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6032. Min Act: -0.1700
Data Index: 3043889 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6032. Min Act: -0.1700
Data Index: 1989512 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6032. Min Act: -0.1700
Data Index: 251786 (Open Web Text)
Max Activating Token Index: 402
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.5720. Min Act: -0.1700
Data Index: 4631552 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.5720. Min Act: -0.1700
Data Index: 3401780 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.6032. Min Act: -0.1700
Data Index: 1987482 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0720. Min Range: -8.0720
Max Act: 7.5407. Min Act: -0.1700
Data Index: 3057565 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #19