Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2895 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1938. Min Range: -7.1938
Max Act: 7.1938. Min Act: -0.1700
Data Index: 7602184 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1938. Min Range: -7.1938
Max Act: 7.0375. Min Act: -0.1700
Data Index: 4825874 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.9438. Min Act: -0.1700
Data Index: 6320977 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.9125. Min Act: -0.1700
Data Index: 4043994 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.8813. Min Act: -0.1700
Data Index: 1375054 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.8188. Min Act: -0.1700
Data Index: 3205509 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.8500. Min Act: -0.1700
Data Index: 5166278 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.8188. Min Act: -0.1700
Data Index: 7123738 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.7875. Min Act: -0.1700
Data Index: 1466441 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.7250. Min Act: -0.1700
Data Index: 1433180 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.7250. Min Act: -0.1700
Data Index: 8410680 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.7250. Min Act: -0.1700
Data Index: 8546077 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.6938. Min Act: -0.1700
Data Index: 8253503 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.6625. Min Act: -0.1700
Data Index: 6550169 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.6938. Min Act: -0.1700
Data Index: 1433176 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.6938. Min Act: -0.1700
Data Index: 6340006 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.6000. Min Act: -0.1700
Data Index: 3814580 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.6000. Min Act: -0.1700
Data Index: 3449521 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.5688. Min Act: -0.1700
Data Index: 1320036 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1938. Min Range: -7.1938
Max Act: 6.5375. Min Act: -0.1700
Data Index: 4663074 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #19