Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3836 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.5807. Min Act: -0.1700
Data Index: 875678 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.4870. Min Act: -0.1700
Data Index: 8580448 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.4870. Min Act: -0.1700
Data Index: 6431632 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.4245. Min Act: -0.1700
Data Index: 2499689 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.4245. Min Act: -0.1700
Data Index: 2859738 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.3932. Min Act: -0.1700
Data Index: 363920 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.3620. Min Act: -0.1700
Data Index: 6599571 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.3307. Min Act: -0.1700
Data Index: 5856427 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.3307. Min Act: -0.1700
Data Index: 2751620 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.3307. Min Act: -0.1700
Data Index: 4690803 (Open Web Text)
Max Activating Token Index: 290
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.2682. Min Act: -0.1700
Data Index: 1815509 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.3307. Min Act: -0.1700
Data Index: 2838750 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.2057. Min Act: -0.1700
Data Index: 6751292 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.2370. Min Act: -0.1700
Data Index: 4950010 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.2370. Min Act: -0.1700
Data Index: 584322 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.2057. Min Act: -0.1700
Data Index: 4289219 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.1745. Min Act: -0.1700
Data Index: 8123475 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.1745. Min Act: -0.1700
Data Index: 4175536 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.1432. Min Act: -0.1700
Data Index: 6583921 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5807. Min Range: -6.5807
Max Act: 6.1120. Min Act: -0.1700
Data Index: 4934065 (Open Web Text)
Max Activating Token Index: 653
Click toggle to see full text
Truncated
Full Text #19