Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6353 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0104. Min Range: -9.0104
Max Act: 9.0104. Min Act: -0.1700
Data Index: 6985873 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.8854. Min Act: -0.1700
Data Index: 60566 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.8229. Min Act: -0.1700
Data Index: 8449851 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6979. Min Act: -0.1700
Data Index: 4773517 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 1010031 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 5586229 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 1762985 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 8718708 (Open Web Text)
Max Activating Token Index: 751
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 7731843 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 7602654 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 8525258 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 1698588 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6354. Min Act: -0.1700
Data Index: 7717908 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.6979. Min Act: -0.1700
Data Index: 2696547 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.5104. Min Act: -0.1700
Data Index: 8309591 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.5729. Min Act: -0.1700
Data Index: 2714205 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.5104. Min Act: -0.1700
Data Index: 2907828 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.5729. Min Act: -0.1700
Data Index: 3437138 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.5104. Min Act: -0.1700
Data Index: 6684433 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0104. Min Range: -9.0104
Max Act: 8.5729. Min Act: -0.1700
Data Index: 7606426 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19