Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1572 in Layer 35
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 10.3251. Min Range: -10.3251
Max Act: 10.3251. Min Act: -0.1700
Data Index: 5658329 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.3251. Min Range: -10.3251
Max Act: 10.1376. Min Act: -0.1700
Data Index: 1737156 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.3251. Min Range: -10.3251
Max Act: 10.0126. Min Act: -0.1700
Data Index: 3550656 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.8876. Min Act: -0.1700
Data Index: 7245756 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.8876. Min Act: -0.1700
Data Index: 2918831 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.8251. Min Act: -0.1700
Data Index: 4315496 (Open Web Text)
Max Activating Token Index: 736
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.6376. Min Act: -0.1700
Data Index: 8503109 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.6376. Min Act: -0.1700
Data Index: 1302973 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.6376. Min Act: -0.1700
Data Index: 5687069 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.5751. Min Act: -0.1700
Data Index: 4569075 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.5126. Min Act: -0.1700
Data Index: 240121 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.4501. Min Act: -0.1700
Data Index: 5499807 (Open Web Text)
Max Activating Token Index: 249
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.3876. Min Act: -0.1700
Data Index: 4061715 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.3876. Min Act: -0.1700
Data Index: 4888032 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.3876. Min Act: -0.1700
Data Index: 7914834 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.3251. Min Act: -0.1700
Data Index: 4889606 (Open Web Text)
Max Activating Token Index: 680
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.3251. Min Act: -0.1700
Data Index: 1447412 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.3251. Min Act: -0.1700
Data Index: 306773 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.2626. Min Act: -0.1700
Data Index: 5752650 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.3251. Min Range: -10.3251
Max Act: 9.2626. Min Act: -0.1700
Data Index: 5005783 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #19