Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 242 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.4818. Min Act: -0.1700
Data Index: 6034288 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.3568. Min Act: -0.1700
Data Index: 1000959 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.3568. Min Act: -0.1700
Data Index: 7036292 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.2631. Min Act: -0.1700
Data Index: 1973154 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.2631. Min Act: -0.1700
Data Index: 8357615 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.2318. Min Act: -0.1700
Data Index: 4775752 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.2318. Min Act: -0.1700
Data Index: 6598406 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.2006. Min Act: -0.1700
Data Index: 3022337 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1693. Min Act: -0.1700
Data Index: 6032512 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1693. Min Act: -0.1700
Data Index: 8002298 (Open Web Text)
Max Activating Token Index: 38
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1693. Min Act: -0.1700
Data Index: 2590338 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1381. Min Act: -0.1700
Data Index: 2089985 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1693. Min Act: -0.1700
Data Index: 1885926 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1068. Min Act: -0.1700
Data Index: 7191433 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1068. Min Act: -0.1700
Data Index: 4065353 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1381. Min Act: -0.1700
Data Index: 540629 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1068. Min Act: -0.1700
Data Index: 2272706 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.1381. Min Act: -0.1700
Data Index: 4566947 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.0756. Min Act: -0.1700
Data Index: 119537 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4818. Min Range: -5.4818
Max Act: 5.0756. Min Act: -0.1700
Data Index: 6467054 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #19