Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2692 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.9211. Min Act: -0.1700
Data Index: 3285188 (Open Web Text)
Max Activating Token Index: 569
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.8586. Min Act: -0.1700
Data Index: 6241827 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.4836. Min Act: -0.1700
Data Index: 2212375 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.4211. Min Act: -0.1700
Data Index: 1589903 (Open Web Text)
Max Activating Token Index: 802
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.3586. Min Act: -0.1700
Data Index: 3840814 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2648. Min Act: -0.1700
Data Index: 8411460 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2648. Min Act: -0.1700
Data Index: 2704428 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2648. Min Act: -0.1700
Data Index: 1509102 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2648. Min Act: -0.1700
Data Index: 6884349 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2336. Min Act: -0.1700
Data Index: 706794 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2336. Min Act: -0.1700
Data Index: 8769713 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2336. Min Act: -0.1700
Data Index: 54125 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.2336. Min Act: -0.1700
Data Index: 6292331 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.1711. Min Act: -0.1700
Data Index: 5450988 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.1398. Min Act: -0.1700
Data Index: 5386246 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.1398. Min Act: -0.1700
Data Index: 358709 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.1398. Min Act: -0.1700
Data Index: 4760530 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.1398. Min Act: -0.1700
Data Index: 6921560 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.1398. Min Act: -0.1700
Data Index: 1298449 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9211. Min Range: -6.9211
Max Act: 6.0773. Min Act: -0.1700
Data Index: 6667275 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #19