Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3424 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.8504. Min Act: -0.1700
Data Index: 6217138 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.7879. Min Act: -0.1700
Data Index: 3941773 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.7879. Min Act: -0.1700
Data Index: 2114324 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.7879. Min Act: -0.1700
Data Index: 4793551 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.7879. Min Act: -0.1700
Data Index: 4539685 (Open Web Text)
Max Activating Token Index: 689
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.6629. Min Act: -0.1700
Data Index: 4793550 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.6629. Min Act: -0.1700
Data Index: 7782562 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.6629. Min Act: -0.1700
Data Index: 5783091 (Open Web Text)
Max Activating Token Index: 273
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.6629. Min Act: -0.1700
Data Index: 8793449 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.4754. Min Act: -0.1700
Data Index: 886074 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.4754. Min Act: -0.1700
Data Index: 7110764 (Open Web Text)
Max Activating Token Index: 220
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2879. Min Act: -0.1700
Data Index: 5097548 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2879. Min Act: -0.1700
Data Index: 3043724 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2879. Min Act: -0.1700
Data Index: 495080 (Open Web Text)
Max Activating Token Index: 357
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2879. Min Act: -0.1700
Data Index: 2077667 (Open Web Text)
Max Activating Token Index: 115
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2879. Min Act: -0.1700
Data Index: 6134721 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2254. Min Act: -0.1700
Data Index: 7532917 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.2254. Min Act: -0.1700
Data Index: 8682396 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.1629. Min Act: -0.1700
Data Index: 4584982 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8504. Min Range: -8.8504
Max Act: 8.1316. Min Act: -0.1700
Data Index: 6512196 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #19