Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 524 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.8079. Min Range: -6.8079
Max Act: 6.8079. Min Act: -0.1700
Data Index: 7107232 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.8079. Min Range: -6.8079
Max Act: 6.4016. Min Act: -0.1700
Data Index: 7573465 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.8079. Min Range: -6.8079
Max Act: 6.1829. Min Act: -0.1700
Data Index: 6919133 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9641. Min Act: -0.1700
Data Index: 5755904 (Open Web Text)
Max Activating Token Index: 934
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9641. Min Act: -0.1700
Data Index: 6044067 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9329. Min Act: -0.1700
Data Index: 6699579 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9641. Min Act: -0.1700
Data Index: 1574945 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9641. Min Act: -0.1700
Data Index: 4716396 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9016. Min Act: -0.1700
Data Index: 5495637 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.9329. Min Act: -0.1700
Data Index: 6826326 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.8704. Min Act: -0.1700
Data Index: 7236703 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 2002815 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 814149 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 6360818 (Open Web Text)
Max Activating Token Index: 630
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.8079. Min Act: -0.1700
Data Index: 66801 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.8391. Min Act: -0.1700
Data Index: 5513357 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.7766. Min Act: -0.1700
Data Index: 7615570 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.7766. Min Act: -0.1700
Data Index: 746980 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.7766. Min Act: -0.1700
Data Index: 3336627 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.8079. Min Range: -6.8079
Max Act: 5.7454. Min Act: -0.1700
Data Index: 788208 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19