Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1898 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2462. Min Range: -6.2462
Max Act: 6.2462. Min Act: -0.1700
Data Index: 7753607 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2462. Min Range: -6.2462
Max Act: 6.2150. Min Act: -0.1700
Data Index: 8207092 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2462. Min Range: -6.2462
Max Act: 6.1212. Min Act: -0.1700
Data Index: 5660550 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2462. Min Range: -6.2462
Max Act: 6.0900. Min Act: -0.1700
Data Index: 5615984 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2462. Min Range: -6.2462
Max Act: 6.0587. Min Act: -0.1700
Data Index: 6760010 (Open Web Text)
Max Activating Token Index: 635
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9962. Min Act: -0.1700
Data Index: 1837881 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9962. Min Act: -0.1700
Data Index: 2227280 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9650. Min Act: -0.1700
Data Index: 608340 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9962. Min Act: -0.1700
Data Index: 4980060 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9650. Min Act: -0.1700
Data Index: 4014241 (Open Web Text)
Max Activating Token Index: 837
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9650. Min Act: -0.1700
Data Index: 4170942 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9337. Min Act: -0.1700
Data Index: 7004970 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9650. Min Act: -0.1700
Data Index: 6377975 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9337. Min Act: -0.1687
Data Index: 2800623 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9025. Min Act: -0.1700
Data Index: 3368397 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9025. Min Act: -0.1700
Data Index: 1761033 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9025. Min Act: -0.1700
Data Index: 6900211 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9025. Min Act: -0.1700
Data Index: 4107678 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.9025. Min Act: -0.1700
Data Index: 6490293 (Open Web Text)
Max Activating Token Index: 127
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2462. Min Range: -6.2462
Max Act: 5.8400. Min Act: -0.1700
Data Index: 5797145 (Open Web Text)
Max Activating Token Index: 676
Click toggle to see full text
Truncated
Full Text #19