Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5778 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.8427. Min Act: -0.1700
Data Index: 4163227 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.7177. Min Act: -0.1700
Data Index: 4708130 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.7177. Min Act: -0.1700
Data Index: 896508 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6864. Min Act: -0.1700
Data Index: 1226983 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6864. Min Act: -0.1700
Data Index: 1965609 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6552. Min Act: -0.1700
Data Index: 4904435 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6552. Min Act: -0.1700
Data Index: 6673680 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6552. Min Act: -0.1700
Data Index: 1934326 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6239. Min Act: -0.1700
Data Index: 8664520 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5927. Min Act: -0.1700
Data Index: 1425110 (Open Web Text)
Max Activating Token Index: 104
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6239. Min Act: -0.1700
Data Index: 2803559 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5927. Min Act: -0.1700
Data Index: 2829884 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5927. Min Act: -0.1700
Data Index: 2410042 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.6239. Min Act: -0.1700
Data Index: 6253018 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5927. Min Act: -0.1700
Data Index: 3570508 (Open Web Text)
Max Activating Token Index: 145
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5302. Min Act: -0.1700
Data Index: 2213712 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5614. Min Act: -0.1700
Data Index: 2468872 (Open Web Text)
Max Activating Token Index: 45
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5614. Min Act: -0.1700
Data Index: 1175530 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5614. Min Act: -0.1700
Data Index: 5380484 (Open Web Text)
Max Activating Token Index: 52
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8427. Min Range: -6.8427
Max Act: 6.5302. Min Act: -0.1700
Data Index: 5186752 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #19