Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2554 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1285. Min Range: -6.1285
Max Act: 6.1285. Min Act: -0.1700
Data Index: 5638428 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1285. Min Range: -6.1285
Max Act: 6.0035. Min Act: -0.1700
Data Index: 8416030 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1285. Min Range: -6.1285
Max Act: 6.0035. Min Act: -0.1700
Data Index: 8255688 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.9097. Min Act: -0.1700
Data Index: 8148013 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.8785. Min Act: -0.1700
Data Index: 2982462 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.8785. Min Act: -0.1700
Data Index: 3004321 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.8472. Min Act: -0.1700
Data Index: 5385769 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.8472. Min Act: -0.1700
Data Index: 5618684 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.8160. Min Act: -0.1700
Data Index: 7022123 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 855635 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7847. Min Act: -0.1700
Data Index: 4488378 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 6067454 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 7118133 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 1190112 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 3776010 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7535. Min Act: -0.1700
Data Index: 7567537 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7222. Min Act: -0.1700
Data Index: 100146 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.7222. Min Act: -0.1700
Data Index: 1165458 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.6910. Min Act: -0.1700
Data Index: 4583840 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1285. Min Range: -6.1285
Max Act: 5.6910. Min Act: -0.1700
Data Index: 2660100 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #19