Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 43 in Layer 13
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.7742. Min Act: -0.1700
Data Index: 151307 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.6492. Min Act: -0.1700
Data Index: 5510051 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.6180. Min Act: -0.1700
Data Index: 363746 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.6180. Min Act: -0.1700
Data Index: 2005966 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.5555. Min Act: -0.1700
Data Index: 507446 (Open Web Text)
Max Activating Token Index: 113
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.5555. Min Act: -0.1700
Data Index: 3112875 (Open Web Text)
Max Activating Token Index: 465
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.5242. Min Act: -0.1700
Data Index: 5841245 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.4930. Min Act: -0.1700
Data Index: 7096162 (Open Web Text)
Max Activating Token Index: 888
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.4617. Min Act: -0.1700
Data Index: 2637661 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.4305. Min Act: -0.1700
Data Index: 1179339 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.4305. Min Act: -0.1700
Data Index: 1114920 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.4305. Min Act: -0.1700
Data Index: 4663806 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3992. Min Act: -0.1700
Data Index: 2001504 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3992. Min Act: -0.1700
Data Index: 435462 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3992. Min Act: -0.1700
Data Index: 6634356 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3680. Min Act: -0.1700
Data Index: 522960 (Open Web Text)
Max Activating Token Index: 695
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3367. Min Act: -0.1700
Data Index: 1723902 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3367. Min Act: -0.1700
Data Index: 1791830 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3367. Min Act: -0.1700
Data Index: 3768733 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7742. Min Range: -6.7742
Max Act: 6.3367. Min Act: -0.1700
Data Index: 7863882 (Open Web Text)
Max Activating Token Index: 20
Click toggle to see full text
Truncated
Full Text #19