Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3816 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8726. Min Act: -0.1700
Data Index: 5971804 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8414. Min Act: -0.1700
Data Index: 4826796 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8726. Min Act: -0.1700
Data Index: 4935779 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8414. Min Act: -0.1700
Data Index: 2792863 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8101. Min Act: -0.1700
Data Index: 7085431 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8101. Min Act: -0.1700
Data Index: 6566866 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8101. Min Act: -0.1700
Data Index: 7436379 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8101. Min Act: -0.1700
Data Index: 4338526 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.8101. Min Act: -0.1700
Data Index: 6731267 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 8660799 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 8367005 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 8261507 (Open Web Text)
Max Activating Token Index: 474
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 8127464 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 4508210 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 2181931 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 7249574 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 1601889 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7788. Min Act: -0.1700
Data Index: 2725394 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7475. Min Act: -0.1700
Data Index: 361512 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8726. Min Range: -3.8726
Max Act: 3.7163. Min Act: -0.1700
Data Index: 6271771 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #19