Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4802 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2986. Min Range: -6.2986
Max Act: 6.2986. Min Act: -0.1700
Data Index: 1772313 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.8924. Min Act: -0.1700
Data Index: 5448891 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.8611. Min Act: -0.1700
Data Index: 4719664 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.8299. Min Act: -0.1700
Data Index: 1799007 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7674. Min Act: -0.1700
Data Index: 4670639 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7674. Min Act: -0.1700
Data Index: 2884884 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7674. Min Act: -0.1700
Data Index: 6924152 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7049. Min Act: -0.1700
Data Index: 277431 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7049. Min Act: -0.1700
Data Index: 2377678 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7049. Min Act: -0.1700
Data Index: 870689 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.7049. Min Act: -0.1700
Data Index: 3562438 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.6424. Min Act: -0.1700
Data Index: 1146450 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.6111. Min Act: -0.1700
Data Index: 2962382 (Open Web Text)
Max Activating Token Index: 275
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.6424. Min Act: -0.1700
Data Index: 6440447 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.5799. Min Act: -0.1700
Data Index: 344825 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.5799. Min Act: -0.1700
Data Index: 6997109 (Open Web Text)
Max Activating Token Index: 37
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.5486. Min Act: -0.1700
Data Index: 6400495 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.5799. Min Act: -0.1700
Data Index: 5438922 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.5799. Min Act: -0.1700
Data Index: 1466919 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2986. Min Range: -6.2986
Max Act: 5.5486. Min Act: -0.1700
Data Index: 1809127 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #19