Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2750 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2062. Min Range: -6.2062
Max Act: 6.2062. Min Act: -0.1700
Data Index: 5691208 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2062. Min Range: -6.2062
Max Act: 6.0187. Min Act: -0.1700
Data Index: 7706337 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.9875. Min Act: -0.1700
Data Index: 4290425 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.9875. Min Act: -0.1700
Data Index: 6825578 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.9250. Min Act: -0.1700
Data Index: 5806713 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.8625. Min Act: -0.1700
Data Index: 8311354 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.8312. Min Act: -0.1700
Data Index: 7026632 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.8312. Min Act: -0.1700
Data Index: 7935703 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.8000. Min Act: -0.1700
Data Index: 6413386 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.8000. Min Act: -0.1700
Data Index: 3377470 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.8000. Min Act: -0.1700
Data Index: 1619505 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7687. Min Act: -0.1700
Data Index: 7874274 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7375. Min Act: -0.1700
Data Index: 8128493 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7687. Min Act: -0.1700
Data Index: 638760 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7062. Min Act: -0.1700
Data Index: 7213795 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7375. Min Act: -0.1700
Data Index: 2005970 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7375. Min Act: -0.1700
Data Index: 1149158 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7375. Min Act: -0.1700
Data Index: 5268834 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7375. Min Act: -0.1700
Data Index: 8501810 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2062. Min Range: -6.2062
Max Act: 5.7375. Min Act: -0.1700
Data Index: 8754363 (Open Web Text)
Max Activating Token Index: 107
Click toggle to see full text
Truncated
Full Text #19