Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4863 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.7805. Min Act: -0.1700
Data Index: 6661715 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.7180. Min Act: -0.1700
Data Index: 2714060 (Open Web Text)
Max Activating Token Index: 592
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.6867. Min Act: -0.1700
Data Index: 6661711 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.6242. Min Act: -0.1700
Data Index: 2068740 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.5930. Min Act: -0.1700
Data Index: 1571529 (Open Web Text)
Max Activating Token Index: 274
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.4367. Min Act: -0.1700
Data Index: 6661712 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.4367. Min Act: -0.1700
Data Index: 6661714 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.4367. Min Act: -0.1700
Data Index: 6756955 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.4055. Min Act: -0.1700
Data Index: 6922707 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.3430. Min Act: -0.1700
Data Index: 858825 (Open Web Text)
Max Activating Token Index: 86
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.3117. Min Act: -0.1700
Data Index: 2103231 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.3117. Min Act: -0.1700
Data Index: 1577401 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.3117. Min Act: -0.1700
Data Index: 147555 (Open Web Text)
Max Activating Token Index: 714
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.2805. Min Act: -0.1700
Data Index: 2579292 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.2805. Min Act: -0.1700
Data Index: 2017327 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.2805. Min Act: -0.1700
Data Index: 7357365 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.2805. Min Act: -0.1700
Data Index: 6100392 (Open Web Text)
Max Activating Token Index: 326
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.2805. Min Act: -0.1700
Data Index: 4533912 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.2492. Min Act: -0.1700
Data Index: 904219 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7805. Min Range: -7.7805
Max Act: 7.1867. Min Act: -0.1700
Data Index: 4710416 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #19