Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3439 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.7435. Min Act: -0.1700
Data Index: 3805423 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.7435. Min Act: -0.1700
Data Index: 2240425 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.6810. Min Act: -0.1700
Data Index: 3143646 (Open Web Text)
Max Activating Token Index: 259
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.6497. Min Act: -0.1700
Data Index: 2486573 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.6184. Min Act: -0.1700
Data Index: 7062826 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.6184. Min Act: -0.1700
Data Index: 3648328 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.6184. Min Act: -0.1700
Data Index: 1346565 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5871. Min Act: -0.1700
Data Index: 7961580 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5871. Min Act: -0.1700
Data Index: 7748185 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 8146647 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 1875785 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 2624578 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 8486124 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 2549477 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 4586615 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 7911024 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 6642244 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 5868687 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5558. Min Act: -0.1700
Data Index: 5027314 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.7435. Min Range: -3.7435
Max Act: 3.5245. Min Act: -0.1700
Data Index: 4788801 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #19