Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1720 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.1785. Min Act: -0.1700
Data Index: 2943022 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.1313. Min Act: -0.1700
Data Index: 4377012 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.1155. Min Act: -0.1700
Data Index: 2070881 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.1155. Min Act: -0.1700
Data Index: 1266675 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0998. Min Act: -0.1700
Data Index: 8041154 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0840. Min Act: -0.1700
Data Index: 2530698 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0840. Min Act: -0.1700
Data Index: 308005 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0682. Min Act: -0.1700
Data Index: 5776077 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0524. Min Act: -0.1700
Data Index: 3231270 (Open Web Text)
Max Activating Token Index: 30
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0524. Min Act: -0.1700
Data Index: 7264780 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0524. Min Act: -0.1700
Data Index: 8618919 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0367. Min Act: -0.1700
Data Index: 7375901 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0367. Min Act: -0.1700
Data Index: 8688481 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0367. Min Act: -0.1700
Data Index: 543225 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0209. Min Act: -0.1700
Data Index: 1248410 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0209. Min Act: -0.1700
Data Index: 5248001 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0209. Min Act: -0.1700
Data Index: 3389098 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0209. Min Act: -0.1700
Data Index: 4884500 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0209. Min Act: -0.1700
Data Index: 7208654 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1785. Min Range: -3.1785
Max Act: 3.0051. Min Act: -0.1700
Data Index: 6271390 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #19