Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2714 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.7648. Min Act: -0.1700
Data Index: 1716884 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.7023. Min Act: -0.1700
Data Index: 6850833 (Open Web Text)
Max Activating Token Index: 904
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.5148. Min Act: -0.1700
Data Index: 2801939 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.4211. Min Act: -0.1700
Data Index: 674881 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.3273. Min Act: -0.1700
Data Index: 2197795 (Open Web Text)
Max Activating Token Index: 960
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.3273. Min Act: -0.1700
Data Index: 5770805 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2961. Min Act: -0.1700
Data Index: 3645829 (Open Web Text)
Max Activating Token Index: 748
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2961. Min Act: -0.1700
Data Index: 1268441 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2648. Min Act: -0.1700
Data Index: 8378236 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2648. Min Act: -0.1700
Data Index: 2985688 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2961. Min Act: -0.1700
Data Index: 522582 (Open Web Text)
Max Activating Token Index: 712
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 7015981 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 7090349 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 4013896 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 1755763 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 7469073 (Open Web Text)
Max Activating Token Index: 495
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 1569673 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 7629441 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2336. Min Act: -0.1700
Data Index: 6870855 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7648. Min Range: -5.7648
Max Act: 5.2023. Min Act: -0.1700
Data Index: 2344623 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #19