Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2213 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1962. Min Range: -8.1962
Max Act: 8.1962. Min Act: -0.1700
Data Index: 4121518 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1962. Min Range: -8.1962
Max Act: 8.1962. Min Act: -0.1700
Data Index: 5923719 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1962. Min Range: -8.1962
Max Act: 8.1337. Min Act: -0.1700
Data Index: 7658416 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1962. Min Range: -8.1962
Max Act: 8.1337. Min Act: -0.1700
Data Index: 7268457 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1962. Min Range: -8.1962
Max Act: 8.0087. Min Act: -0.1700
Data Index: 1314856 (Open Web Text)
Max Activating Token Index: 55
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1962. Min Range: -8.1962
Max Act: 8.0087. Min Act: -0.1700
Data Index: 2750201 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.8837. Min Act: -0.1700
Data Index: 547843 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.8837. Min Act: -0.1700
Data Index: 728509 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.8212. Min Act: -0.1700
Data Index: 5510368 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.7587. Min Act: -0.1700
Data Index: 8628170 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.7587. Min Act: -0.1700
Data Index: 7131745 (Open Web Text)
Max Activating Token Index: 231
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6649. Min Act: -0.1700
Data Index: 2987443 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 4659787 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 3401919 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 5915163 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 154237 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6962. Min Act: -0.1700
Data Index: 5160891 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6649. Min Act: -0.1700
Data Index: 5406977 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6649. Min Act: -0.1700
Data Index: 3864458 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1962. Min Range: -8.1962
Max Act: 7.6649. Min Act: -0.1700
Data Index: 823656 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19