Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3295 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.5095. Min Act: -0.1700
Data Index: 5603731 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4781. Min Act: -0.1700
Data Index: 5044516 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4781. Min Act: -0.1700
Data Index: 3304184 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4468. Min Act: -0.1700
Data Index: 5530187 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4468. Min Act: -0.1700
Data Index: 1893483 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4468. Min Act: -0.1700
Data Index: 7872704 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4468. Min Act: -0.1700
Data Index: 6000633 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4468. Min Act: -0.1700
Data Index: 660843 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 2415514 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 1505935 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 3804007 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 2207142 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 5291915 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 5467343 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.4155. Min Act: -0.1700
Data Index: 1108936 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.3841. Min Act: -0.1700
Data Index: 405630 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.3841. Min Act: -0.1700
Data Index: 3725493 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.3841. Min Act: -0.1700
Data Index: 4430047 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.3841. Min Act: -0.1700
Data Index: 5269732 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.5095. Min Range: -3.5095
Max Act: 3.3841. Min Act: -0.1700
Data Index: 1698693 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19