Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3614 in Layer 23
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.3811. Min Act: -0.1700
Data Index: 2369003 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.2873. Min Act: -0.1700
Data Index: 2242780 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.1936. Min Act: -0.1700
Data Index: 1108436 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.2248. Min Act: -0.1700
Data Index: 177470 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.1936. Min Act: -0.1700
Data Index: 4915952 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.1936. Min Act: -0.1700
Data Index: 4062401 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.1311. Min Act: -0.1700
Data Index: 837013 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.1311. Min Act: -0.1700
Data Index: 8152723 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0686. Min Act: -0.1700
Data Index: 8342838 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0686. Min Act: -0.1700
Data Index: 930526 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0373. Min Act: -0.1700
Data Index: 5722024 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0373. Min Act: -0.1700
Data Index: 7022055 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0061. Min Act: -0.1700
Data Index: 966609 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0061. Min Act: -0.1700
Data Index: 7746829 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0061. Min Act: -0.1700
Data Index: 2270808 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3811. Min Range: -6.3811
Max Act: 6.0061. Min Act: -0.1700
Data Index: 1516030 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3811. Min Range: -6.3811
Max Act: 5.9748. Min Act: -0.1700
Data Index: 4303518 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3811. Min Range: -6.3811
Max Act: 5.9748. Min Act: -0.1700
Data Index: 1899711 (Open Web Text)
Max Activating Token Index: 718
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3811. Min Range: -6.3811
Max Act: 5.9748. Min Act: -0.1700
Data Index: 6490423 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3811. Min Range: -6.3811
Max Act: 5.9748. Min Act: -0.1700
Data Index: 6102180 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #19