Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1948 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7137. Min Range: -8.7137
Max Act: 8.7137. Min Act: -0.1700
Data Index: 8498352 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7137. Min Range: -8.7137
Max Act: 8.0262. Min Act: -0.1700
Data Index: 5912221 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.9950. Min Act: -0.1700
Data Index: 4912028 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.9012. Min Act: -0.1700
Data Index: 4470508 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.7137. Min Act: -0.1700
Data Index: 5828941 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.6825. Min Act: -0.1700
Data Index: 720435 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.6825. Min Act: -0.1700
Data Index: 6814760 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.6200. Min Act: -0.1700
Data Index: 5768342 (Open Web Text)
Max Activating Token Index: 692
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.6200. Min Act: -0.1700
Data Index: 6608911 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.5262. Min Act: -0.1700
Data Index: 8508933 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.4950. Min Act: -0.1700
Data Index: 7110600 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.4325. Min Act: -0.1700
Data Index: 8238824 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 1665656 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.3387. Min Act: -0.1700
Data Index: 1995630 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.3075. Min Act: -0.1700
Data Index: 2138752 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.3075. Min Act: -0.1700
Data Index: 286475 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.2450. Min Act: -0.1700
Data Index: 2868348 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.2762. Min Act: -0.1700
Data Index: 5816204 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.2450. Min Act: -0.1700
Data Index: 7196374 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7137. Min Range: -8.7137
Max Act: 7.2762. Min Act: -0.1700
Data Index: 3451779 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19