Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4791 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.7100. Min Act: -0.1700
Data Index: 5836181 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.5850. Min Act: -0.1700
Data Index: 3026099 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.5850. Min Act: -0.1700
Data Index: 1501715 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.5850. Min Act: -0.1700
Data Index: 1547778 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.5225. Min Act: -0.1700
Data Index: 8780387 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.4913. Min Act: -0.1700
Data Index: 4233543 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.4600. Min Act: -0.1700
Data Index: 1567713 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.4600. Min Act: -0.1700
Data Index: 1405465 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.4600. Min Act: -0.1700
Data Index: 4304667 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.4288. Min Act: -0.1700
Data Index: 6985763 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.3975. Min Act: -0.1700
Data Index: 8751672 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.3350. Min Act: -0.1700
Data Index: 3304455 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.3350. Min Act: -0.1700
Data Index: 6612055 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.2725. Min Act: -0.1700
Data Index: 121477 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.2725. Min Act: -0.1700
Data Index: 3738938 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.3350. Min Act: -0.1700
Data Index: 1053376 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.3038. Min Act: -0.1700
Data Index: 6175900 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.2725. Min Act: -0.1700
Data Index: 3976873 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.2725. Min Act: -0.1700
Data Index: 2940437 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7100. Min Range: -6.7100
Max Act: 6.2725. Min Act: -0.1700
Data Index: 1472541 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #19