Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 52 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.2419. Min Act: -0.1700
Data Index: 6009983 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.1794. Min Act: -0.1700
Data Index: 3530667 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.1482. Min Act: -0.1700
Data Index: 3292952 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.0544. Min Act: -0.1700
Data Index: 585231 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.0857. Min Act: -0.1700
Data Index: 3250909 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.0544. Min Act: -0.1700
Data Index: 283539 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.0544. Min Act: -0.1700
Data Index: 3029433 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.0232. Min Act: -0.1700
Data Index: 2131827 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2419. Min Range: -6.2419
Max Act: 6.0232. Min Act: -0.1700
Data Index: 3399616 (Open Web Text)
Max Activating Token Index: 212
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9919. Min Act: -0.1700
Data Index: 7761975 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9919. Min Act: -0.1700
Data Index: 8721910 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9607. Min Act: -0.1700
Data Index: 2101301 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9607. Min Act: -0.1700
Data Index: 2188244 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9607. Min Act: -0.1700
Data Index: 842226 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9607. Min Act: -0.1700
Data Index: 125914 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9294. Min Act: -0.1700
Data Index: 3418176 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9294. Min Act: -0.1700
Data Index: 4089080 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9294. Min Act: -0.1700
Data Index: 1304794 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.9294. Min Act: -0.1700
Data Index: 2329920 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2419. Min Range: -6.2419
Max Act: 5.8982. Min Act: -0.1700
Data Index: 4003824 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #19