Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5642 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.0532. Min Range: -7.0532
Max Act: 7.0532. Min Act: -0.1700
Data Index: 4278347 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.7719. Min Act: -0.1700
Data Index: 2700703 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.7094. Min Act: -0.1700
Data Index: 7746639 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.6469. Min Act: -0.1700
Data Index: 7063860 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5844. Min Act: -0.1700
Data Index: 5104139 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.5219. Min Act: -0.1700
Data Index: 8578955 (Open Web Text)
Max Activating Token Index: 611
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.3969. Min Act: -0.1700
Data Index: 8343354 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2719. Min Act: -0.1700
Data Index: 8154867 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.3032. Min Act: -0.1700
Data Index: 4079763 (Open Web Text)
Max Activating Token Index: 292
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.3032. Min Act: -0.1700
Data Index: 124428 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2719. Min Act: -0.1700
Data Index: 2565542 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2407. Min Act: -0.1700
Data Index: 8695780 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2094. Min Act: -0.1700
Data Index: 4331660 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2407. Min Act: -0.1700
Data Index: 851383 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2094. Min Act: -0.1700
Data Index: 4875203 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.1782. Min Act: -0.1700
Data Index: 2455431 (Open Web Text)
Max Activating Token Index: 777
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.2094. Min Act: -0.1700
Data Index: 7382661 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.1469. Min Act: -0.1700
Data Index: 4581582 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.1469. Min Act: -0.1700
Data Index: 614822 (Open Web Text)
Max Activating Token Index: 928
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0532. Min Range: -7.0532
Max Act: 6.1157. Min Act: -0.1700
Data Index: 1966005 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19