Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3543 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.7635. Min Act: -0.1700
Data Index: 2280172 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.7010. Min Act: -0.1700
Data Index: 5641426 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.5448. Min Act: -0.1700
Data Index: 2922415 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.3885. Min Act: -0.1700
Data Index: 2643468 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.3885. Min Act: -0.1700
Data Index: 6610218 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.3885. Min Act: -0.1700
Data Index: 5652415 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.2948. Min Act: -0.1700
Data Index: 128425 (Open Web Text)
Max Activating Token Index: 707
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.2635. Min Act: -0.1700
Data Index: 5015792 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.2010. Min Act: -0.1700
Data Index: 3284901 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.2010. Min Act: -0.1700
Data Index: 6927973 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.1697. Min Act: -0.1700
Data Index: 7770127 (Open Web Text)
Max Activating Token Index: 121
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.1385. Min Act: -0.1700
Data Index: 559308 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.1072. Min Act: -0.1700
Data Index: 4877426 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0760. Min Act: -0.1700
Data Index: 497518 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0760. Min Act: -0.1700
Data Index: 7556689 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0447. Min Act: -0.1700
Data Index: 5015801 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0447. Min Act: -0.1700
Data Index: 7227446 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0135. Min Act: -0.1700
Data Index: 2344588 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0135. Min Act: -0.1700
Data Index: 3772836 (Open Web Text)
Max Activating Token Index: 757
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7635. Min Range: -4.7635
Max Act: 4.0135. Min Act: -0.1700
Data Index: 5015800 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #19