Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2204 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3473. Min Range: -8.3473
Max Act: 8.3473. Min Act: -0.1700
Data Index: 2085747 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3473. Min Range: -8.3473
Max Act: 8.0660. Min Act: -0.1700
Data Index: 8226936 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.8785. Min Act: -0.1700
Data Index: 1149933 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.8473. Min Act: -0.1700
Data Index: 8363592 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.8160. Min Act: -0.1700
Data Index: 4114854 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.7848. Min Act: -0.1700
Data Index: 2757266 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.7223. Min Act: -0.1700
Data Index: 4993974 (Open Web Text)
Max Activating Token Index: 686
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.7223. Min Act: -0.1700
Data Index: 5245832 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.7535. Min Act: -0.1700
Data Index: 1301694 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.6910. Min Act: -0.1700
Data Index: 6335058 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.6910. Min Act: -0.1700
Data Index: 5289384 (Open Web Text)
Max Activating Token Index: 784
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.6910. Min Act: -0.1700
Data Index: 8105128 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.6910. Min Act: -0.1700
Data Index: 923779 (Open Web Text)
Max Activating Token Index: 365
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.5973. Min Act: -0.1700
Data Index: 6851341 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.6285. Min Act: -0.1700
Data Index: 1040803 (Open Web Text)
Max Activating Token Index: 442
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.5973. Min Act: -0.1700
Data Index: 2878841 (Open Web Text)
Max Activating Token Index: 916
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.6285. Min Act: -0.1700
Data Index: 7654103 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.5973. Min Act: -0.1700
Data Index: 8048729 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.5973. Min Act: -0.1700
Data Index: 3497382 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3473. Min Range: -8.3473
Max Act: 7.5660. Min Act: -0.1700
Data Index: 4553824 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #19