Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1687 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4812. Min Act: -0.1700
Data Index: 1282806 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4342. Min Act: -0.1700
Data Index: 1451347 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4029. Min Act: -0.1700
Data Index: 2941720 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4029. Min Act: -0.1700
Data Index: 6298172 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4029. Min Act: -0.1700
Data Index: 8370748 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4029. Min Act: -0.1700
Data Index: 7724081 (Open Web Text)
Max Activating Token Index: 599
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3872. Min Act: -0.1700
Data Index: 2508220 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4029. Min Act: -0.1700
Data Index: 8262744 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.4029. Min Act: -0.1700
Data Index: 6856180 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3715. Min Act: -0.1700
Data Index: 4016639 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3401. Min Act: -0.1700
Data Index: 7166299 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3245. Min Act: -0.1700
Data Index: 1930428 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3245. Min Act: -0.1700
Data Index: 346623 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3245. Min Act: -0.1700
Data Index: 6301122 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3088. Min Act: -0.1700
Data Index: 4116039 (Open Web Text)
Max Activating Token Index: 450
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3088. Min Act: -0.1700
Data Index: 5615644 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.3088. Min Act: -0.1700
Data Index: 2910879 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.2931. Min Act: -0.1700
Data Index: 6146296 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.2774. Min Act: -0.1700
Data Index: 3625003 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4812. Min Range: -3.4812
Max Act: 3.2774. Min Act: -0.1700
Data Index: 4389392 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #19