Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3610 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.8716. Min Act: -0.1700
Data Index: 4074424 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.8404. Min Act: -0.1700
Data Index: 4346791 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.8404. Min Act: -0.1700
Data Index: 5825094 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.8091. Min Act: -0.1700
Data Index: 5404788 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.8091. Min Act: -0.1700
Data Index: 5783801 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.7779. Min Act: -0.1700
Data Index: 2304954 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6841. Min Act: -0.1700
Data Index: 810449 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.7466. Min Act: -0.1700
Data Index: 4869418 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.7154. Min Act: -0.1700
Data Index: 4268229 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6841. Min Act: -0.1700
Data Index: 2011401 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6841. Min Act: -0.1700
Data Index: 6896454 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6529. Min Act: -0.1700
Data Index: 6494916 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6841. Min Act: -0.1700
Data Index: 4539905 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6529. Min Act: -0.1700
Data Index: 4145037 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6216. Min Act: -0.1700
Data Index: 2288013 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.6216. Min Act: -0.1700
Data Index: 1583802 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.5904. Min Act: -0.1700
Data Index: 6748333 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.5591. Min Act: -0.1700
Data Index: 2920256 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.5591. Min Act: -0.1700
Data Index: 2488890 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8716. Min Range: -5.8716
Max Act: 5.5279. Min Act: -0.1700
Data Index: 4074577 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #19