Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6365 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.8973. Min Act: -0.1700
Data Index: 4942090 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.5223. Min Act: -0.1700
Data Index: 294219 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.4285. Min Act: -0.1700
Data Index: 7927444 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.4285. Min Act: -0.1700
Data Index: 1251643 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.3660. Min Act: -0.1700
Data Index: 5418860 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.3035. Min Act: -0.1700
Data Index: 5133261 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.2723. Min Act: -0.1700
Data Index: 1624243 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.2723. Min Act: -0.1700
Data Index: 8682026 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.2410. Min Act: -0.1700
Data Index: 2126179 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.2098. Min Act: -0.1700
Data Index: 4879809 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1785. Min Act: -0.1700
Data Index: 8073574 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 5316935 (Open Web Text)
Max Activating Token Index: 554
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 26751 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 1149798 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 5978442 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 6042228 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1473. Min Act: -0.1700
Data Index: 7137157 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1160. Min Act: -0.1700
Data Index: 950675 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1160. Min Act: -0.1700
Data Index: 2442136 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8973. Min Range: -6.8973
Max Act: 6.1160. Min Act: -0.1700
Data Index: 5272315 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #19