Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6235 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9720. Min Act: -0.1700
Data Index: 3065709 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9551. Min Act: -0.1700
Data Index: 7273940 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9466. Min Act: -0.1695
Data Index: 4990383 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9381. Min Act: -0.1700
Data Index: 3165826 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9381. Min Act: -0.1700
Data Index: 1289838 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9381. Min Act: -0.1700
Data Index: 5048119 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9381. Min Act: -0.1698
Data Index: 8398385 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9296. Min Act: -0.1700
Data Index: 4161298 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9126. Min Act: -0.1700
Data Index: 1620801 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9126. Min Act: -0.1700
Data Index: 6194559 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9040. Min Act: -0.1700
Data Index: 21165 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.9040. Min Act: -0.1700
Data Index: 7066562 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8955. Min Act: -0.1700
Data Index: 1779298 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8955. Min Act: -0.1698
Data Index: 2431891 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8870. Min Act: -0.1694
Data Index: 4729719 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8870. Min Act: -0.1700
Data Index: 5440035 (Open Web Text)
Max Activating Token Index: 825
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8784. Min Act: -0.1700
Data Index: 66756 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8784. Min Act: -0.1700
Data Index: 1919857 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8784. Min Act: -0.1697
Data Index: 4093763 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 1.9720. Min Range: -1.9720
Max Act: 1.8699. Min Act: -0.1700
Data Index: 2218168 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #19