Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5734 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.7143. Min Act: -0.1700
Data Index: 7957912 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.3705. Min Act: -0.1700
Data Index: 4921850 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.4018. Min Act: -0.1700
Data Index: 7119617 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.3080. Min Act: -0.1700
Data Index: 4387078 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.2455. Min Act: -0.1700
Data Index: 2044571 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.2455. Min Act: -0.1700
Data Index: 1049171 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.1830. Min Act: -0.1700
Data Index: 6730032 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.1518. Min Act: -0.1700
Data Index: 794028 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.1830. Min Act: -0.1700
Data Index: 7370686 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.2143. Min Act: -0.1700
Data Index: 515310 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0893. Min Act: -0.1700
Data Index: 2266954 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0893. Min Act: -0.1700
Data Index: 7057081 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0580. Min Act: -0.1700
Data Index: 5087815 (Open Web Text)
Max Activating Token Index: 810
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0268. Min Act: -0.1700
Data Index: 2266953 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0268. Min Act: -0.1700
Data Index: 4735829 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0268. Min Act: -0.1700
Data Index: 8132471 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7143. Min Range: -7.7143
Max Act: 7.0268. Min Act: -0.1700
Data Index: 8740422 (Open Web Text)
Max Activating Token Index: 999
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7143. Min Range: -7.7143
Max Act: 6.9955. Min Act: -0.1700
Data Index: 2903144 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7143. Min Range: -7.7143
Max Act: 6.9643. Min Act: -0.1700
Data Index: 224212 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7143. Min Range: -7.7143
Max Act: 6.9643. Min Act: -0.1700
Data Index: 281110 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #19