Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3407 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.1641. Min Range: -6.1641
Max Act: 6.1641. Min Act: -0.1700
Data Index: 8425429 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1641. Min Range: -6.1641
Max Act: 6.0391. Min Act: -0.1700
Data Index: 3636661 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1641. Min Range: -6.1641
Max Act: 6.0078. Min Act: -0.1700
Data Index: 1844007 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1641. Min Range: -6.1641
Max Act: 6.0078. Min Act: -0.1700
Data Index: 5605965 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.8828. Min Act: -0.1700
Data Index: 2949227 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.8516. Min Act: -0.1700
Data Index: 8265841 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.8203. Min Act: -0.1700
Data Index: 5455545 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 2197805 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.7266. Min Act: -0.1700
Data Index: 1781712 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.7266. Min Act: -0.1700
Data Index: 2828685 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.7266. Min Act: -0.1700
Data Index: 7597593 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.7578. Min Act: -0.1700
Data Index: 4187341 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 769629 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 7142429 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 4504635 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 7184161 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 7102629 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 5597015 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6953. Min Act: -0.1700
Data Index: 34674 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1641. Min Range: -6.1641
Max Act: 5.6641. Min Act: -0.1700
Data Index: 4654694 (Open Web Text)
Max Activating Token Index: 197
Click toggle to see full text
Truncated
Full Text #19