Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2025 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3641. Min Range: -7.3641
Max Act: 7.3641. Min Act: -0.1700
Data Index: 4637259 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3641. Min Range: -7.3641
Max Act: 7.1453. Min Act: -0.1700
Data Index: 7002851 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3641. Min Range: -7.3641
Max Act: 7.1453. Min Act: -0.1700
Data Index: 1658841 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3641. Min Range: -7.3641
Max Act: 7.1141. Min Act: -0.1700
Data Index: 1760034 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3641. Min Range: -7.3641
Max Act: 7.1141. Min Act: -0.1700
Data Index: 3804471 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3641. Min Range: -7.3641
Max Act: 7.0516. Min Act: -0.1700
Data Index: 8758438 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.9891. Min Act: -0.1700
Data Index: 833599 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.9891. Min Act: -0.1700
Data Index: 3253274 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.9578. Min Act: -0.1700
Data Index: 2940249 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.9266. Min Act: -0.1700
Data Index: 7940756 (Open Web Text)
Max Activating Token Index: 957
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.9266. Min Act: -0.1700
Data Index: 1203718 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.9266. Min Act: -0.1700
Data Index: 2273782 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 8780962 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 4977645 (Open Web Text)
Max Activating Token Index: 522
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 7105818 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 2021055 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 357861 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 4722599 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8641. Min Act: -0.1700
Data Index: 6060440 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3641. Min Range: -7.3641
Max Act: 6.8328. Min Act: -0.1700
Data Index: 751660 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #19