Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4636 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.7831. Min Act: -0.1700
Data Index: 7414658 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.5331. Min Act: -0.1700
Data Index: 3995684 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.4081. Min Act: -0.1700
Data Index: 972814 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.3456. Min Act: -0.1700
Data Index: 4825287 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.3144. Min Act: -0.1700
Data Index: 5350655 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.3144. Min Act: -0.1700
Data Index: 4518283 (Open Web Text)
Max Activating Token Index: 973
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2831. Min Act: -0.1700
Data Index: 634984 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2831. Min Act: -0.1700
Data Index: 4638664 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2831. Min Act: -0.1700
Data Index: 6077346 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2206. Min Act: -0.1700
Data Index: 2521594 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2206. Min Act: -0.1700
Data Index: 1967222 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2206. Min Act: -0.1700
Data Index: 2198784 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2206. Min Act: -0.1700
Data Index: 2123999 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.2206. Min Act: -0.1700
Data Index: 3295925 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.1894. Min Act: -0.1700
Data Index: 5134703 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.1894. Min Act: -0.1700
Data Index: 7733373 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.1894. Min Act: -0.1700
Data Index: 2319213 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.1269. Min Act: -0.1700
Data Index: 8334548 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.1581. Min Act: -0.1700
Data Index: 5239320 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7831. Min Range: -7.7831
Max Act: 7.1269. Min Act: -0.1700
Data Index: 6462831 (Open Web Text)
Max Activating Token Index: 267
Click toggle to see full text
Truncated
Full Text #19