Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3446 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2718. Min Range: -9.2718
Max Act: 9.2718. Min Act: -0.1700
Data Index: 4252943 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2718. Min Range: -9.2718
Max Act: 9.0218. Min Act: -0.1700
Data Index: 1847740 (Open Web Text)
Max Activating Token Index: 640
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.8343. Min Act: -0.1700
Data Index: 8060790 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.8343. Min Act: -0.1700
Data Index: 3568926 (Open Web Text)
Max Activating Token Index: 839
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.7093. Min Act: -0.1700
Data Index: 8277299 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.7718. Min Act: -0.1700
Data Index: 1479418 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.6468. Min Act: -0.1700
Data Index: 6886070 (Open Web Text)
Max Activating Token Index: 537
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.6468. Min Act: -0.1700
Data Index: 2508584 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.5843. Min Act: -0.1700
Data Index: 2203769 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.5843. Min Act: -0.1700
Data Index: 5910652 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.5218. Min Act: -0.1700
Data Index: 3513329 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.5218. Min Act: -0.1700
Data Index: 4757980 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.5218. Min Act: -0.1700
Data Index: 2935502 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.5218. Min Act: -0.1700
Data Index: 7327122 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.4593. Min Act: -0.1700
Data Index: 7343583 (Open Web Text)
Max Activating Token Index: 589
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.4593. Min Act: -0.1700
Data Index: 311368 (Open Web Text)
Max Activating Token Index: 448
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.3968. Min Act: -0.1700
Data Index: 1730049 (Open Web Text)
Max Activating Token Index: 222
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.3968. Min Act: -0.1700
Data Index: 3723836 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.3968. Min Act: -0.1700
Data Index: 419778 (Open Web Text)
Max Activating Token Index: 1019
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2718. Min Range: -9.2718
Max Act: 8.3968. Min Act: -0.1700
Data Index: 7730167 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #19