Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5977 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.4981. Min Act: -0.1700
Data Index: 1936139 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.2481. Min Act: -0.1700
Data Index: 8598657 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1856. Min Act: -0.1700
Data Index: 1528279 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1544. Min Act: -0.1700
Data Index: 418113 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1231. Min Act: -0.1700
Data Index: 1751672 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1231. Min Act: -0.1700
Data Index: 5068459 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.1231. Min Act: -0.1700
Data Index: 3845571 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4981. Min Range: -6.4981
Max Act: 6.0919. Min Act: -0.1700
Data Index: 460236 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9981. Min Act: -0.1700
Data Index: 2570468 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9669. Min Act: -0.1700
Data Index: 7329127 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9669. Min Act: -0.1700
Data Index: 1454008 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9356. Min Act: -0.1700
Data Index: 8536135 (Open Web Text)
Max Activating Token Index: 348
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9044. Min Act: -0.1700
Data Index: 5665381 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9044. Min Act: -0.1700
Data Index: 7894824 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.9044. Min Act: -0.1700
Data Index: 3967668 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.8731. Min Act: -0.1700
Data Index: 5308279 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.8731. Min Act: -0.1700
Data Index: 7676375 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.8419. Min Act: -0.1700
Data Index: 6961308 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.8419. Min Act: -0.1700
Data Index: 4473462 (Open Web Text)
Max Activating Token Index: 289
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4981. Min Range: -6.4981
Max Act: 5.8419. Min Act: -0.1700
Data Index: 7360389 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #19