Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3138 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2923. Min Range: -6.2923
Max Act: 6.2923. Min Act: -0.1700
Data Index: 2003112 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2923. Min Range: -6.2923
Max Act: 6.0110. Min Act: -0.1700
Data Index: 1244088 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.9485. Min Act: -0.1700
Data Index: 7964818 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.8860. Min Act: -0.1700
Data Index: 2822561 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.8235. Min Act: -0.1700
Data Index: 5797947 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.7610. Min Act: -0.1700
Data Index: 4778043 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.7610. Min Act: -0.1700
Data Index: 3295242 (Open Web Text)
Max Activating Token Index: 685
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.7610. Min Act: -0.1700
Data Index: 6770892 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6985. Min Act: -0.1700
Data Index: 5456988 (Open Web Text)
Max Activating Token Index: 87
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 5280099 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6985. Min Act: -0.1700
Data Index: 8220030 (Open Web Text)
Max Activating Token Index: 268
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6985. Min Act: -0.1700
Data Index: 7497569 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 3982999 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6360. Min Act: -0.1700
Data Index: 5544529 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 842039 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6985. Min Act: -0.1700
Data Index: 4868176 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6673. Min Act: -0.1700
Data Index: 5084386 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6360. Min Act: -0.1700
Data Index: 1430716 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6360. Min Act: -0.1700
Data Index: 6115984 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2923. Min Range: -6.2923
Max Act: 5.6048. Min Act: -0.1700
Data Index: 6181005 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19