Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3529 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 4578513 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 5133815 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.8074. Min Act: -0.1691
Data Index: 2337865 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 1763754 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 1647422 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.8074. Min Act: -0.1700
Data Index: 438543 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 4692605 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 1413779 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 4662580 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 726172 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 3133021 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 2281326 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.8074. Min Act: -0.1700
Data Index: 3084791 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 4065520 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.8074. Min Act: -0.1699
Data Index: 2017371 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 2575116 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 3823983 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.8074. Min Act: -0.1698
Data Index: 1990816 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.8074. Min Act: -0.1700
Data Index: 992129 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.8074. Min Range: -2.8074
Max Act: 2.7915. Min Act: -0.1700
Data Index: 148631 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19