Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6392 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.8558. Min Act: -0.1700
Data Index: 8323261 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.7620. Min Act: -0.1700
Data Index: 4995036 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.7308. Min Act: -0.1700
Data Index: 6434902 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.6370. Min Act: -0.1700
Data Index: 7294880 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.6058. Min Act: -0.1700
Data Index: 2801921 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.5120. Min Act: -0.1700
Data Index: 3964951 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.4183. Min Act: -0.1700
Data Index: 204184 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.3558. Min Act: -0.1700
Data Index: 501253 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2933. Min Act: -0.1700
Data Index: 5006747 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2933. Min Act: -0.1700
Data Index: 5431701 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2620. Min Act: -0.1700
Data Index: 4362865 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2933. Min Act: -0.1700
Data Index: 8085504 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2620. Min Act: -0.1700
Data Index: 5990499 (Open Web Text)
Max Activating Token Index: 81
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2620. Min Act: -0.1700
Data Index: 284616 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2308. Min Act: -0.1700
Data Index: 1282706 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.2308. Min Act: -0.1700
Data Index: 924103 (Open Web Text)
Max Activating Token Index: 340
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.1995. Min Act: -0.1700
Data Index: 4995035 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.1683. Min Act: -0.1700
Data Index: 4027607 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.1370. Min Act: -0.1700
Data Index: 3216050 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8558. Min Range: -6.8558
Max Act: 6.1370. Min Act: -0.1700
Data Index: 5578007 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #19