Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3576 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.4599. Min Act: -0.1700
Data Index: 6067105 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.3974. Min Act: -0.1700
Data Index: 3176815 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.3974. Min Act: -0.1700
Data Index: 1641603 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.2099. Min Act: -0.1700
Data Index: 7726411 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.1474. Min Act: -0.1700
Data Index: 5773945 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.1474. Min Act: -0.1700
Data Index: 8093107 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.0849. Min Act: -0.1700
Data Index: 7735677 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.0849. Min Act: -0.1700
Data Index: 8383564 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.0224. Min Act: -0.1700
Data Index: 4849971 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.0224. Min Act: -0.1700
Data Index: 2546317 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.0224. Min Act: -0.1700
Data Index: 842185 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4599. Min Range: -8.4599
Max Act: 8.0224. Min Act: -0.1700
Data Index: 1279210 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.9599. Min Act: -0.1700
Data Index: 7934866 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.8974. Min Act: -0.1700
Data Index: 4498454 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.8974. Min Act: -0.1700
Data Index: 6161287 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.8349. Min Act: -0.1700
Data Index: 5438761 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.8974. Min Act: -0.1700
Data Index: 7176024 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.8349. Min Act: -0.1700
Data Index: 6382238 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.8349. Min Act: -0.1700
Data Index: 2612853 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4599. Min Range: -8.4599
Max Act: 7.7724. Min Act: -0.1700
Data Index: 787775 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #19