Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4934 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.7835. Min Act: -0.1700
Data Index: 7781407 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 108139 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1695
Data Index: 408904 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 4895779 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 1884735 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 4942521 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 4814853 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 309275 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.7210. Min Act: -0.1700
Data Index: 3582831 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1695
Data Index: 4475704 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 1711373 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2833678 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 1710971 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 2623016 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1697
Data Index: 2998062 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1698
Data Index: 1672433 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 5162619 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1700
Data Index: 769183 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1648
Data Index: 1507358 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7835. Min Range: -5.7835
Max Act: 5.6898. Min Act: -0.1693
Data Index: 4357044 (Open Web Text)
Max Activating Token Index: 1
Click toggle to see full text
Truncated
Full Text #19