Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5118 in Layer 11
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.7274. Min Act: -0.1700
Data Index: 2138763 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.6961. Min Act: -0.1700
Data Index: 7205818 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5711. Min Act: -0.1700
Data Index: 7956571 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5711. Min Act: -0.1700
Data Index: 6109771 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5399. Min Act: -0.1700
Data Index: 1444330 (Open Web Text)
Max Activating Token Index: 79
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5399. Min Act: -0.1700
Data Index: 6125989 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5399. Min Act: -0.1700
Data Index: 538349 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5086. Min Act: -0.1700
Data Index: 725443 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5086. Min Act: -0.1700
Data Index: 1474932 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5086. Min Act: -0.1700
Data Index: 591817 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.5086. Min Act: -0.1700
Data Index: 1036254 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4461. Min Act: -0.1700
Data Index: 5016104 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4461. Min Act: -0.1700
Data Index: 1017320 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4461. Min Act: -0.1700
Data Index: 1161040 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4149. Min Act: -0.1700
Data Index: 5072006 (Open Web Text)
Max Activating Token Index: 228
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4149. Min Act: -0.1700
Data Index: 7013114 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4149. Min Act: -0.1700
Data Index: 6059961 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4149. Min Act: -0.1700
Data Index: 450293 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4149. Min Act: -0.1700
Data Index: 3942939 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7274. Min Range: -4.7274
Max Act: 4.4149. Min Act: -0.1700
Data Index: 6989748 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #19