Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5192 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3978. Min Range: -7.3978
Max Act: 7.3978. Min Act: -0.1700
Data Index: 3902353 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.9603. Min Act: -0.1700
Data Index: 89555 (Open Web Text)
Max Activating Token Index: 1020
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.8040. Min Act: -0.1700
Data Index: 8371214 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.6790. Min Act: -0.1700
Data Index: 6738922 (Open Web Text)
Max Activating Token Index: 202
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.6790. Min Act: -0.1700
Data Index: 4288855 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.6790. Min Act: -0.1700
Data Index: 427333 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.6478. Min Act: -0.1700
Data Index: 4022673 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.6165. Min Act: -0.1700
Data Index: 33874 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5853. Min Act: -0.1700
Data Index: 8500146 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5853. Min Act: -0.1700
Data Index: 2908682 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5540. Min Act: -0.1700
Data Index: 7130456 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5540. Min Act: -0.1700
Data Index: 8526671 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5540. Min Act: -0.1700
Data Index: 5283529 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5228. Min Act: -0.1700
Data Index: 307101 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5228. Min Act: -0.1700
Data Index: 2249799 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5228. Min Act: -0.1700
Data Index: 1512412 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.5228. Min Act: -0.1700
Data Index: 6288398 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.4915. Min Act: -0.1700
Data Index: 2310184 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.4915. Min Act: -0.1700
Data Index: 1611409 (Open Web Text)
Max Activating Token Index: 857
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3978. Min Range: -7.3978
Max Act: 6.4915. Min Act: -0.1700
Data Index: 2819251 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #19