Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1812 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.0743. Min Range: -8.0743
Max Act: 8.0743. Min Act: -0.1700
Data Index: 2935961 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.7618. Min Act: -0.1700
Data Index: 1356957 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.7618. Min Act: -0.1700
Data Index: 2016008 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.6368. Min Act: -0.1700
Data Index: 2409715 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.6993. Min Act: -0.1700
Data Index: 2554800 (Open Web Text)
Max Activating Token Index: 735
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.6368. Min Act: -0.1700
Data Index: 7851222 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.6368. Min Act: -0.1700
Data Index: 586013 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.6368. Min Act: -0.1700
Data Index: 7265655 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.6368. Min Act: -0.1700
Data Index: 1007970 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.5430. Min Act: -0.1700
Data Index: 3595168 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.5430. Min Act: -0.1700
Data Index: 3089065 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.5118. Min Act: -0.1700
Data Index: 4595049 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.5430. Min Act: -0.1700
Data Index: 5527764 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.4805. Min Act: -0.1700
Data Index: 4943511 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.5118. Min Act: -0.1700
Data Index: 8390089 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.4180. Min Act: -0.1700
Data Index: 679789 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.4180. Min Act: -0.1700
Data Index: 3944502 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.4493. Min Act: -0.1700
Data Index: 8744026 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.4180. Min Act: -0.1700
Data Index: 1054260 (Open Web Text)
Max Activating Token Index: 405
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.0743. Min Range: -8.0743
Max Act: 7.3868. Min Act: -0.1700
Data Index: 156713 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #19