Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1186 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.6552. Min Act: -0.1700
Data Index: 8786874 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.5927. Min Act: -0.1700
Data Index: 1126087 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.4052. Min Act: -0.1700
Data Index: 5108783 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.2802. Min Act: -0.1700
Data Index: 877223 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.2802. Min Act: -0.1700
Data Index: 4600302 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.2177. Min Act: -0.1700
Data Index: 8786872 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.1552. Min Act: -0.1700
Data Index: 3192908 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.1552. Min Act: -0.1700
Data Index: 1087808 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.1552. Min Act: -0.1700
Data Index: 6361170 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.1552. Min Act: -0.1700
Data Index: 857222 (Open Web Text)
Max Activating Token Index: 397
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.0927. Min Act: -0.1700
Data Index: 3192907 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.0615. Min Act: -0.1700
Data Index: 7441604 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.6552. Min Range: -8.6552
Max Act: 8.0615. Min Act: -0.1700
Data Index: 2965264 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.9990. Min Act: -0.1700
Data Index: 622474 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.9990. Min Act: -0.1700
Data Index: 2943562 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.9677. Min Act: -0.1700
Data Index: 2965279 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.9365. Min Act: -0.1700
Data Index: 4121291 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.9365. Min Act: -0.1700
Data Index: 8257208 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.8740. Min Act: -0.1700
Data Index: 5363209 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.6552. Min Range: -8.6552
Max Act: 7.8427. Min Act: -0.1700
Data Index: 2201219 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #19