Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2510 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.4848. Min Act: -0.1700
Data Index: 1540132 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.4223. Min Act: -0.1700
Data Index: 849129 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.4223. Min Act: -0.1700
Data Index: 7611537 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.3910. Min Act: -0.1700
Data Index: 881010 (Open Web Text)
Max Activating Token Index: 819
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.3598. Min Act: -0.1700
Data Index: 7053872 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.3598. Min Act: -0.1700
Data Index: 6183747 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.3285. Min Act: -0.1700
Data Index: 2573481 (Open Web Text)
Max Activating Token Index: 157
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.3285. Min Act: -0.1700
Data Index: 8628791 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.3285. Min Act: -0.1700
Data Index: 7412180 (Open Web Text)
Max Activating Token Index: 783
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.2973. Min Act: -0.1700
Data Index: 3826356 (Open Web Text)
Max Activating Token Index: 254
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.1723. Min Act: -0.1700
Data Index: 6083589 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.1098. Min Act: -0.1700
Data Index: 4260826 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0785. Min Act: -0.1700
Data Index: 2311350 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0473. Min Act: -0.1700
Data Index: 1768792 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0473. Min Act: -0.1700
Data Index: 468358 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0473. Min Act: -0.1700
Data Index: 6406936 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0473. Min Act: -0.1700
Data Index: 1277267 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0473. Min Act: -0.1700
Data Index: 1404645 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0785. Min Act: -0.1700
Data Index: 7779078 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4848. Min Range: -6.4848
Max Act: 6.0160. Min Act: -0.1700
Data Index: 1789748 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #19