Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5263 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1847. Min Range: -7.1847
Max Act: 7.1847. Min Act: -0.1700
Data Index: 8339535 (Open Web Text)
Max Activating Token Index: 439
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.9347. Min Act: -0.1700
Data Index: 3420338 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.8409. Min Act: -0.1700
Data Index: 5601611 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.8409. Min Act: -0.1700
Data Index: 2535983 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.8097. Min Act: -0.1700
Data Index: 3821671 (Open Web Text)
Max Activating Token Index: 209
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.7784. Min Act: -0.1700
Data Index: 3143042 (Open Web Text)
Max Activating Token Index: 583
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.7159. Min Act: -0.1700
Data Index: 7374011 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.7472. Min Act: -0.1700
Data Index: 8277053 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6847. Min Act: -0.1700
Data Index: 1333402 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6847. Min Act: -0.1700
Data Index: 4762529 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6534. Min Act: -0.1700
Data Index: 6299779 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6534. Min Act: -0.1700
Data Index: 1757649 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6534. Min Act: -0.1700
Data Index: 3978254 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6534. Min Act: -0.1700
Data Index: 6768267 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.6222. Min Act: -0.1700
Data Index: 5695765 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.5909. Min Act: -0.1700
Data Index: 7817830 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.5909. Min Act: -0.1700
Data Index: 1295795 (Open Web Text)
Max Activating Token Index: 301
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.5909. Min Act: -0.1700
Data Index: 4427571 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.5597. Min Act: -0.1700
Data Index: 5747953 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1847. Min Range: -7.1847
Max Act: 6.5909. Min Act: -0.1700
Data Index: 1193416 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #19