Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5408 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.8139. Min Act: -0.1700
Data Index: 8508933 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.8139. Min Act: -0.1700
Data Index: 2750139 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7513. Min Act: -0.1700
Data Index: 7753123 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7513. Min Act: -0.1700
Data Index: 1639762 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7513. Min Act: -0.1700
Data Index: 3825418 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7513. Min Act: -0.1700
Data Index: 197308 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7513. Min Act: -0.1700
Data Index: 8384573 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7513. Min Act: -0.1700
Data Index: 5927850 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7200. Min Act: -0.1700
Data Index: 3886917 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7200. Min Act: -0.1700
Data Index: 7501065 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7200. Min Act: -0.1700
Data Index: 3891742 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7200. Min Act: -0.1700
Data Index: 2709679 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.7200. Min Act: -0.1700
Data Index: 2680904 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 1857082 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 8500439 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 7915351 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 1040642 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 2778782 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 3989916 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8139. Min Range: -3.8139
Max Act: 3.6887. Min Act: -0.1700
Data Index: 3741155 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #19