Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3087 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2569. Min Range: -7.2569
Max Act: 7.2569. Min Act: -0.1700
Data Index: 1804512 (Open Web Text)
Max Activating Token Index: 808
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2569. Min Range: -7.2569
Max Act: 7.1006. Min Act: -0.1700
Data Index: 8585699 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2569. Min Range: -7.2569
Max Act: 7.0381. Min Act: -0.1700
Data Index: 1689401 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2569. Min Range: -7.2569
Max Act: 7.0381. Min Act: -0.1700
Data Index: 8227391 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.9756. Min Act: -0.1700
Data Index: 28219 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.8506. Min Act: -0.1700
Data Index: 7109180 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.8506. Min Act: -0.1700
Data Index: 5396769 (Open Web Text)
Max Activating Token Index: 566
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.8506. Min Act: -0.1700
Data Index: 6516303 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.8506. Min Act: -0.1700
Data Index: 2613886 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.8194. Min Act: -0.1700
Data Index: 3643841 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7881. Min Act: -0.1700
Data Index: 6833856 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7881. Min Act: -0.1700
Data Index: 6943371 (Open Web Text)
Max Activating Token Index: 247
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7881. Min Act: -0.1700
Data Index: 3964765 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7881. Min Act: -0.1700
Data Index: 259326 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7569. Min Act: -0.1700
Data Index: 6576635 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7569. Min Act: -0.1700
Data Index: 2231620 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7256. Min Act: -0.1700
Data Index: 8577806 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.7256. Min Act: -0.1700
Data Index: 192612 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.6944. Min Act: -0.1700
Data Index: 4335530 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2569. Min Range: -7.2569
Max Act: 6.6944. Min Act: -0.1700
Data Index: 4335531 (Open Web Text)
Max Activating Token Index: 884
Click toggle to see full text
Truncated
Full Text #19