Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5632 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2187. Min Range: -8.2187
Max Act: 8.2187. Min Act: -0.1700
Data Index: 3206853 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2187. Min Range: -8.2187
Max Act: 8.1562. Min Act: -0.1700
Data Index: 1157805 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2187. Min Range: -8.2187
Max Act: 8.1250. Min Act: -0.1700
Data Index: 3958831 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.9687. Min Act: -0.1700
Data Index: 7876035 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.9062. Min Act: -0.1700
Data Index: 8735889 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.8750. Min Act: -0.1700
Data Index: 7129081 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.8125. Min Act: -0.1700
Data Index: 3537025 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.8437. Min Act: -0.1700
Data Index: 3866824 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.8125. Min Act: -0.1700
Data Index: 6003964 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.8437. Min Act: -0.1700
Data Index: 3128099 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7812. Min Act: -0.1700
Data Index: 6236931 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7500. Min Act: -0.1700
Data Index: 7276098 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7812. Min Act: -0.1700
Data Index: 2665044 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7812. Min Act: -0.1700
Data Index: 145719 (Open Web Text)
Max Activating Token Index: 56
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7500. Min Act: -0.1700
Data Index: 5128646 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7500. Min Act: -0.1700
Data Index: 7466691 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.7187. Min Act: -0.1700
Data Index: 1219151 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.6875. Min Act: -0.1700
Data Index: 7366114 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.6875. Min Act: -0.1700
Data Index: 7267709 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2187. Min Range: -8.2187
Max Act: 7.6875. Min Act: -0.1700
Data Index: 1644880 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #19