Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2848 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.7649. Min Act: -0.1700
Data Index: 4340715 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.6712. Min Act: -0.1700
Data Index: 4487843 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.5774. Min Act: -0.1700
Data Index: 6180986 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.5462. Min Act: -0.1700
Data Index: 3493500 (Open Web Text)
Max Activating Token Index: 753
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.5149. Min Act: -0.1700
Data Index: 3882824 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4837. Min Act: -0.1700
Data Index: 602886 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4837. Min Act: -0.1700
Data Index: 5218715 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4212. Min Act: -0.1700
Data Index: 4106916 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4212. Min Act: -0.1700
Data Index: 5315195 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4212. Min Act: -0.1700
Data Index: 6921318 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4212. Min Act: -0.1700
Data Index: 7092299 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4212. Min Act: -0.1700
Data Index: 8443796 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.4212. Min Act: -0.1700
Data Index: 5192137 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.3899. Min Act: -0.1700
Data Index: 1419356 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.3899. Min Act: -0.1700
Data Index: 1029605 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.3899. Min Act: -0.1700
Data Index: 1669470 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.3274. Min Act: -0.1700
Data Index: 4932475 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.2962. Min Act: -0.1700
Data Index: 8413044 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.2649. Min Act: -0.1700
Data Index: 6162075 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7649. Min Range: -6.7649
Max Act: 6.2649. Min Act: -0.1700
Data Index: 747927 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #19