Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2721 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1012. Min Range: -5.1012
Max Act: 5.1012. Min Act: -0.1700
Data Index: 8123720 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.8825. Min Act: -0.1700
Data Index: 8001152 (Open Web Text)
Max Activating Token Index: 747
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.8200. Min Act: -0.1700
Data Index: 2260289 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.8512. Min Act: -0.1700
Data Index: 4583008 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.7887. Min Act: -0.1700
Data Index: 8001148 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.7262. Min Act: -0.1700
Data Index: 2132398 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6950. Min Act: -0.1700
Data Index: 2364314 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.7262. Min Act: -0.1700
Data Index: 4778412 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6950. Min Act: -0.1700
Data Index: 8001149 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6950. Min Act: -0.1700
Data Index: 2142720 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6950. Min Act: -0.1700
Data Index: 2820947 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6637. Min Act: -0.1700
Data Index: 5533951 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6637. Min Act: -0.1700
Data Index: 4372039 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6950. Min Act: -0.1700
Data Index: 3127192 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6950. Min Act: -0.1700
Data Index: 5439111 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6637. Min Act: -0.1700
Data Index: 140086 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6325. Min Act: -0.1700
Data Index: 7125923 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6325. Min Act: -0.1700
Data Index: 3165219 (Open Web Text)
Max Activating Token Index: 515
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6012. Min Act: -0.1700
Data Index: 1860287 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1012. Min Range: -5.1012
Max Act: 4.6325. Min Act: -0.1700
Data Index: 4430757 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #19