Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2742 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.5593. Min Range: -9.5593
Max Act: 9.5593. Min Act: -0.1700
Data Index: 4951420 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.5593. Min Range: -9.5593
Max Act: 9.4968. Min Act: -0.1700
Data Index: 7034926 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.5593. Min Range: -9.5593
Max Act: 9.0593. Min Act: -0.1700
Data Index: 8731884 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.8718. Min Act: -0.1700
Data Index: 4472968 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.6218. Min Act: -0.1700
Data Index: 6439977 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.4968. Min Act: -0.1700
Data Index: 6727530 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.4968. Min Act: -0.1700
Data Index: 554843 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.4343. Min Act: -0.1700
Data Index: 6727524 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.2468. Min Act: -0.1700
Data Index: 1986940 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.2156. Min Act: -0.1700
Data Index: 3663632 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.1843. Min Act: -0.1700
Data Index: 8101589 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.1218. Min Act: -0.1700
Data Index: 554826 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.5593. Min Range: -9.5593
Max Act: 8.1218. Min Act: -0.1698
Data Index: 2616849 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.9968. Min Act: -0.1700
Data Index: 701206 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.9656. Min Act: -0.1700
Data Index: 185049 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.9968. Min Act: -0.1700
Data Index: 7469039 (Open Web Text)
Max Activating Token Index: 43
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.9343. Min Act: -0.1700
Data Index: 2274652 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.9343. Min Act: -0.1700
Data Index: 5168713 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.8406. Min Act: -0.1700
Data Index: 5671874 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.5593. Min Range: -9.5593
Max Act: 7.8718. Min Act: -0.1700
Data Index: 5371740 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #19