Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1262 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.8828. Min Act: -0.1700
Data Index: 3988770 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.8516. Min Act: -0.1700
Data Index: 6165537 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.8203. Min Act: -0.1700
Data Index: 7718175 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.6641. Min Act: -0.1700
Data Index: 7226957 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.6328. Min Act: -0.1700
Data Index: 7876960 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.6328. Min Act: -0.1700
Data Index: 2402347 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.6328. Min Act: -0.1700
Data Index: 1902771 (Open Web Text)
Max Activating Token Index: 604
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.6016. Min Act: -0.1700
Data Index: 669708 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5703. Min Act: -0.1700
Data Index: 6116756 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5703. Min Act: -0.1700
Data Index: 5888513 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5391. Min Act: -0.1700
Data Index: 3299482 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5391. Min Act: -0.1700
Data Index: 998981 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5078. Min Act: -0.1700
Data Index: 4125837 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5391. Min Act: -0.1700
Data Index: 3327634 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5391. Min Act: -0.1700
Data Index: 2282236 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.4766. Min Act: -0.1700
Data Index: 6763196 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.5078. Min Act: -0.1700
Data Index: 590699 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.4766. Min Act: -0.1700
Data Index: 6102803 (Open Web Text)
Max Activating Token Index: 141
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.4766. Min Act: -0.1700
Data Index: 1701461 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8828. Min Range: -6.8828
Max Act: 6.4766. Min Act: -0.1700
Data Index: 2909745 (Open Web Text)
Max Activating Token Index: 639
Click toggle to see full text
Truncated
Full Text #19