Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4828 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.5866. Min Act: -0.1700
Data Index: 359255 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.1803. Min Act: -0.1700
Data Index: 6384796 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.1178. Min Act: -0.1700
Data Index: 905602 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.0866. Min Act: -0.1700
Data Index: 2192362 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.0866. Min Act: -0.1700
Data Index: 313672 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.0553. Min Act: -0.1700
Data Index: 5585379 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.0553. Min Act: -0.1700
Data Index: 4138054 (Open Web Text)
Max Activating Token Index: 83
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5866. Min Range: -6.5866
Max Act: 6.0553. Min Act: -0.1700
Data Index: 5692780 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.9928. Min Act: -0.1700
Data Index: 1070689 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.9616. Min Act: -0.1700
Data Index: 351094 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.9616. Min Act: -0.1700
Data Index: 7392683 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8678. Min Act: -0.1700
Data Index: 588267 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8366. Min Act: -0.1700
Data Index: 1124672 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8678. Min Act: -0.1700
Data Index: 4618152 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8991. Min Act: -0.1700
Data Index: 5963156 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8366. Min Act: -0.1700
Data Index: 5644408 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8053. Min Act: -0.1700
Data Index: 6377304 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8053. Min Act: -0.1700
Data Index: 2890817 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.8053. Min Act: -0.1700
Data Index: 6762487 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5866. Min Range: -6.5866
Max Act: 5.7741. Min Act: -0.1700
Data Index: 2429010 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #19