Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5346 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1876. Min Range: -7.1876
Max Act: 7.1876. Min Act: -0.1700
Data Index: 5551808 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1876. Min Range: -7.1876
Max Act: 7.0938. Min Act: -0.1700
Data Index: 3392862 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9376. Min Act: -0.1700
Data Index: 4285663 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9688. Min Act: -0.1700
Data Index: 7181811 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9063. Min Act: -0.1700
Data Index: 6663450 (Open Web Text)
Max Activating Token Index: 167
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9376. Min Act: -0.1700
Data Index: 8399775 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.9063. Min Act: -0.1700
Data Index: 360952 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8438. Min Act: -0.1700
Data Index: 2598701 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7813. Min Act: -0.1700
Data Index: 3388627 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.8126. Min Act: -0.1700
Data Index: 2481564 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7813. Min Act: -0.1700
Data Index: 3828731 (Open Web Text)
Max Activating Token Index: 280
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7188. Min Act: -0.1700
Data Index: 5361435 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.7501. Min Act: -0.1700
Data Index: 8708435 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6876. Min Act: -0.1700
Data Index: 3942214 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6563. Min Act: -0.1700
Data Index: 6813836 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6563. Min Act: -0.1700
Data Index: 3355981 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6251. Min Act: -0.1700
Data Index: 3779982 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6251. Min Act: -0.1700
Data Index: 8422418 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6251. Min Act: -0.1700
Data Index: 6931837 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1876. Min Range: -7.1876
Max Act: 6.6251. Min Act: -0.1700
Data Index: 5395585 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #19