Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5409 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.4752. Min Act: -0.1700
Data Index: 6103303 (Open Web Text)
Max Activating Token Index: 379
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.4752. Min Act: -0.1700
Data Index: 4174076 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.3502. Min Act: -0.1694
Data Index: 4819062 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.4127. Min Act: -0.1700
Data Index: 5180498 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.3502. Min Act: -0.1700
Data Index: 5521295 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.2877. Min Act: -0.1700
Data Index: 4083656 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.2877. Min Act: -0.1700
Data Index: 3107780 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.2252. Min Act: -0.1691
Data Index: 4506628 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.4752. Min Range: -9.4752
Max Act: 9.2877. Min Act: -0.1692
Data Index: 5657381 (Open Web Text)
Max Activating Token Index: 902
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.9752. Min Act: -0.1699
Data Index: 7159511 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.9752. Min Act: -0.1700
Data Index: 477256 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.9127. Min Act: -0.1700
Data Index: 3006692 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.9127. Min Act: -0.1700
Data Index: 5116057 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.9127. Min Act: -0.1700
Data Index: 5657378 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.8502. Min Act: -0.1700
Data Index: 5562285 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.7877. Min Act: -0.1700
Data Index: 6398665 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.7877. Min Act: -0.1700
Data Index: 1663483 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.7877. Min Act: -0.1700
Data Index: 5657382 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.7252. Min Act: -0.1700
Data Index: 4005489 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.4752. Min Range: -9.4752
Max Act: 8.7252. Min Act: -0.1700
Data Index: 1145252 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #19