Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2787 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0949. Min Range: -5.0949
Max Act: 5.0949. Min Act: -0.1700
Data Index: 5197063 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0949. Min Range: -5.0949
Max Act: 5.0324. Min Act: -0.1700
Data Index: 3025032 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0949. Min Range: -5.0949
Max Act: 5.0012. Min Act: -0.1700
Data Index: 4499188 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.9699. Min Act: -0.1700
Data Index: 108466 (Open Web Text)
Max Activating Token Index: 237
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.9387. Min Act: -0.1700
Data Index: 6015404 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.9074. Min Act: -0.1700
Data Index: 7532591 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8762. Min Act: -0.1700
Data Index: 209038 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1700
Data Index: 6593833 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1700
Data Index: 1283609 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1700
Data Index: 7223 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1700
Data Index: 2862171 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1699
Data Index: 5779779 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1700
Data Index: 2064709 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8449. Min Act: -0.1700
Data Index: 1147615 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8137. Min Act: -0.1700
Data Index: 2944658 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8137. Min Act: -0.1700
Data Index: 780717 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8137. Min Act: -0.1700
Data Index: 7116754 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8137. Min Act: -0.1700
Data Index: 730836 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.8137. Min Act: -0.1700
Data Index: 4504481 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0949. Min Range: -5.0949
Max Act: 4.7824. Min Act: -0.1682
Data Index: 1066127 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #19