Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2404 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.5182. Min Act: -0.1700
Data Index: 4313768 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.2682. Min Act: -0.1700
Data Index: 7516407 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.2057. Min Act: -0.1700
Data Index: 8019052 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.1432. Min Act: -0.1700
Data Index: 7706312 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0807. Min Act: -0.1700
Data Index: 7762735 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.1432. Min Act: -0.1700
Data Index: 5203406 (Open Web Text)
Max Activating Token Index: 422
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0807. Min Act: -0.1700
Data Index: 7635868 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0182. Min Act: -0.1700
Data Index: 5481362 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0807. Min Act: -0.1700
Data Index: 5646362 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0182. Min Act: -0.1700
Data Index: 5098707 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0182. Min Act: -0.1700
Data Index: 5897263 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0807. Min Act: -0.1700
Data Index: 3599323 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.5182. Min Range: -10.5182
Max Act: 10.0182. Min Act: -0.1700
Data Index: 2075414 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 4095442 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 1654434 (Open Web Text)
Max Activating Token Index: 910
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 1176359 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 2584966 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 184993 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 894899 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.5182. Min Range: -10.5182
Max Act: 9.9557. Min Act: -0.1700
Data Index: 1901984 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #19