Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5037 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.3629. Min Act: -0.1700
Data Index: 2564223 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.3317. Min Act: -0.1700
Data Index: 4138080 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.2692. Min Act: -0.1700
Data Index: 7847292 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.2379. Min Act: -0.1700
Data Index: 2736486 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.1754. Min Act: -0.1700
Data Index: 421720 (Open Web Text)
Max Activating Token Index: 722
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3629. Min Range: -6.3629
Max Act: 6.0817. Min Act: -0.1700
Data Index: 1918582 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9879. Min Act: -0.1700
Data Index: 5113271 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9254. Min Act: -0.1700
Data Index: 4472920 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.9567. Min Act: -0.1700
Data Index: 8320051 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.8629. Min Act: -0.1700
Data Index: 6952827 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.8629. Min Act: -0.1700
Data Index: 8039604 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.8317. Min Act: -0.1700
Data Index: 2888973 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.8629. Min Act: -0.1700
Data Index: 8503644 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.8317. Min Act: -0.1700
Data Index: 255886 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.7692. Min Act: -0.1700
Data Index: 1462151 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.7692. Min Act: -0.1700
Data Index: 4765266 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.7692. Min Act: -0.1700
Data Index: 5863298 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.7379. Min Act: -0.1700
Data Index: 8518879 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.7692. Min Act: -0.1700
Data Index: 4862944 (Open Web Text)
Max Activating Token Index: 728
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3629. Min Range: -6.3629
Max Act: 5.7067. Min Act: -0.1700
Data Index: 2497843 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #19