Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2264 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.9877. Min Range: -9.9877
Max Act: 9.9877. Min Act: -0.1700
Data Index: 3888053 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.9877. Min Range: -9.9877
Max Act: 9.2377. Min Act: -0.1700
Data Index: 3599736 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.9877. Min Act: -0.1700
Data Index: 3661907 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.9877. Min Act: -0.1700
Data Index: 6196069 (Open Web Text)
Max Activating Token Index: 731
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.9252. Min Act: -0.1700
Data Index: 1284042 (Open Web Text)
Max Activating Token Index: 966
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8627. Min Act: -0.1700
Data Index: 2257967 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8627. Min Act: -0.1700
Data Index: 8019888 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8627. Min Act: -0.1700
Data Index: 1503341 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8627. Min Act: -0.1700
Data Index: 1924270 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8627. Min Act: -0.1700
Data Index: 980739 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8002. Min Act: -0.1700
Data Index: 4079277 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8002. Min Act: -0.1700
Data Index: 5267375 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.8627. Min Act: -0.1700
Data Index: 8535577 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.7377. Min Act: -0.1700
Data Index: 6406449 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.7377. Min Act: -0.1700
Data Index: 1903794 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.7377. Min Act: -0.1700
Data Index: 7264445 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.6752. Min Act: -0.1700
Data Index: 3363121 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.6752. Min Act: -0.1700
Data Index: 1647133 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.7377. Min Act: -0.1700
Data Index: 7388167 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.9877. Min Range: -9.9877
Max Act: 8.7377. Min Act: -0.1700
Data Index: 5143656 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #19