Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 4553 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.4854. Min Act: -0.1700
Data Index: 6643097 (Open Web Text)
Max Activating Token Index: 119
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.3914. Min Act: -0.1700
Data Index: 6500902 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2973. Min Act: -0.1700
Data Index: 5017831 (Open Web Text)
Max Activating Token Index: 178
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2816. Min Act: -0.1700
Data Index: 8058398 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2659. Min Act: -0.1700
Data Index: 3507732 (Open Web Text)
Max Activating Token Index: 632
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2501. Min Act: -0.1700
Data Index: 1647818 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2659. Min Act: -0.1700
Data Index: 2913741 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2344. Min Act: -0.1700
Data Index: 6698251 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2344. Min Act: -0.1700
Data Index: 3438784 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.2030. Min Act: -0.1700
Data Index: 1150541 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1873. Min Act: -0.1700
Data Index: 2631478 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1715. Min Act: -0.1700
Data Index: 8816209 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1873. Min Act: -0.1700
Data Index: 4471798 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1558. Min Act: -0.1700
Data Index: 2160199 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1558. Min Act: -0.1700
Data Index: 5788866 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1558. Min Act: -0.1700
Data Index: 3438783 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1401. Min Act: -0.1700
Data Index: 7453615 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1558. Min Act: -0.1700
Data Index: 2099625 (Open Web Text)
Max Activating Token Index: 148
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1401. Min Act: -0.1700
Data Index: 5043784 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4854. Min Range: -3.4854
Max Act: 3.1401. Min Act: -0.1700
Data Index: 3365812 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #19