Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2673 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0812. Min Range: -6.0812
Max Act: 6.0812. Min Act: -0.1700
Data Index: 4373347 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0812. Min Range: -6.0812
Max Act: 6.0500. Min Act: -0.1700
Data Index: 993936 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.9875. Min Act: -0.1700
Data Index: 824577 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.9562. Min Act: -0.1700
Data Index: 1524466 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.8937. Min Act: -0.1700
Data Index: 7858939 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.8937. Min Act: -0.1700
Data Index: 4060953 (Open Web Text)
Max Activating Token Index: 538
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.8625. Min Act: -0.1700
Data Index: 4920029 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.8000. Min Act: -0.1700
Data Index: 1427505 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7687. Min Act: -0.1700
Data Index: 8466576 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7687. Min Act: -0.1700
Data Index: 1863927 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7687. Min Act: -0.1700
Data Index: 6826607 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7375. Min Act: -0.1700
Data Index: 6432541 (Open Web Text)
Max Activating Token Index: 175
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7375. Min Act: -0.1700
Data Index: 5888463 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7375. Min Act: -0.1700
Data Index: 7360049 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7375. Min Act: -0.1700
Data Index: 5050228 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7375. Min Act: -0.1700
Data Index: 5009169 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.7375. Min Act: -0.1700
Data Index: 1829357 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.6750. Min Act: -0.1700
Data Index: 4650339 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.6750. Min Act: -0.1700
Data Index: 1403317 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0812. Min Range: -6.0812
Max Act: 5.6750. Min Act: -0.1700
Data Index: 2265232 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #19