Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3465 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4104. Min Range: -9.4104
Max Act: 9.4104. Min Act: -0.1700
Data Index: 4892136 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4104. Min Range: -9.4104
Max Act: 9.0354. Min Act: -0.1700
Data Index: 5500218 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 1300083 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.7854. Min Act: -0.1700
Data Index: 1982217 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.7229. Min Act: -0.1700
Data Index: 7901475 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.7229. Min Act: -0.1700
Data Index: 4985135 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.6604. Min Act: -0.1700
Data Index: 1544627 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.6604. Min Act: -0.1700
Data Index: 1718650 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.5979. Min Act: -0.1700
Data Index: 2701755 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.5979. Min Act: -0.1700
Data Index: 3362481 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.5354. Min Act: -0.1700
Data Index: 7255124 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.5354. Min Act: -0.1700
Data Index: 4007703 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4729. Min Act: -0.1700
Data Index: 1586507 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4729. Min Act: -0.1700
Data Index: 8697705 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4104. Min Act: -0.1700
Data Index: 8138634 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4104. Min Act: -0.1700
Data Index: 777586 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4104. Min Act: -0.1700
Data Index: 6390483 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4104. Min Act: -0.1700
Data Index: 527555 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4104. Min Act: -0.1700
Data Index: 4964509 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4104. Min Range: -9.4104
Max Act: 8.4104. Min Act: -0.1700
Data Index: 4184161 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #19