Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6346 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.9688. Min Act: -0.1700
Data Index: 4659923 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.9063. Min Act: -0.1700
Data Index: 6166085 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.9063. Min Act: -0.1700
Data Index: 2152956 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8750. Min Act: -0.1700
Data Index: 3039164 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8437. Min Act: -0.1700
Data Index: 3545344 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8437. Min Act: -0.1700
Data Index: 1319580 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8125. Min Act: -0.1700
Data Index: 7368718 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8125. Min Act: -0.1700
Data Index: 3468713 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8125. Min Act: -0.1700
Data Index: 6279883 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8125. Min Act: -0.1700
Data Index: 3703798 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8125. Min Act: -0.1700
Data Index: 7729747 (Open Web Text)
Max Activating Token Index: 179
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.8125. Min Act: -0.1700
Data Index: 2449846 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7812. Min Act: -0.1700
Data Index: 2923454 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7812. Min Act: -0.1700
Data Index: 2366001 (Open Web Text)
Max Activating Token Index: 962
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7812. Min Act: -0.1700
Data Index: 2923448 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7812. Min Act: -0.1700
Data Index: 682124 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7499. Min Act: -0.1700
Data Index: 309371 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7499. Min Act: -0.1700
Data Index: 2292784 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7030. Min Act: -0.1700
Data Index: 2931873 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9688. Min Range: -3.9688
Max Act: 3.7186. Min Act: -0.1700
Data Index: 758959 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #19