Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5990 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.2718. Min Range: -8.2718
Max Act: 8.2718. Min Act: -0.1700
Data Index: 8239001 (Open Web Text)
Max Activating Token Index: 949
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.2718. Min Range: -8.2718
Max Act: 8.2718. Min Act: -0.1700
Data Index: 2846498 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.2718. Min Range: -8.2718
Max Act: 8.0843. Min Act: -0.1700
Data Index: 4135693 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.2718. Min Range: -8.2718
Max Act: 8.0218. Min Act: -0.1700
Data Index: 4909968 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.8968. Min Act: -0.1700
Data Index: 6213895 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.8655. Min Act: -0.1700
Data Index: 6681978 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.7718. Min Act: -0.1700
Data Index: 7223571 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.7405. Min Act: -0.1700
Data Index: 4902971 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6780. Min Act: -0.1700
Data Index: 2703553 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.7093. Min Act: -0.1700
Data Index: 8201473 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6468. Min Act: -0.1700
Data Index: 721368 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6780. Min Act: -0.1700
Data Index: 2929656 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6468. Min Act: -0.1700
Data Index: 1563781 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6155. Min Act: -0.1700
Data Index: 6169783 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6468. Min Act: -0.1700
Data Index: 4846742 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6155. Min Act: -0.1700
Data Index: 7378740 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6155. Min Act: -0.1700
Data Index: 4905151 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6155. Min Act: -0.1700
Data Index: 174251 (Open Web Text)
Max Activating Token Index: 90
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.6155. Min Act: -0.1700
Data Index: 976581 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.2718. Min Range: -8.2718
Max Act: 7.5530. Min Act: -0.1700
Data Index: 2539424 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #19