Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 675 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.7407. Min Act: -0.1700
Data Index: 8064391 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.6469. Min Act: -0.1700
Data Index: 4724829 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.5219. Min Act: -0.1700
Data Index: 3295253 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3969. Min Act: -0.1700
Data Index: 4012396 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3969. Min Act: -0.1700
Data Index: 4852173 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2719. Min Act: -0.1700
Data Index: 6086516 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.3344. Min Act: -0.1700
Data Index: 5601951 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2719. Min Act: -0.1700
Data Index: 8282541 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2407. Min Act: -0.1700
Data Index: 4121183 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2407. Min Act: -0.1700
Data Index: 8796574 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2407. Min Act: -0.1700
Data Index: 7230688 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2094. Min Act: -0.1700
Data Index: 4574554 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2094. Min Act: -0.1700
Data Index: 2888469 (Open Web Text)
Max Activating Token Index: 482
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2094. Min Act: -0.1700
Data Index: 8579790 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 1102569 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 4984221 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.1782. Min Act: -0.1700
Data Index: 3455742 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2094. Min Act: -0.1700
Data Index: 7600385 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.2094. Min Act: -0.1700
Data Index: 2075359 (Open Web Text)
Max Activating Token Index: 575
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7407. Min Range: -5.7407
Max Act: 5.1157. Min Act: -0.1700
Data Index: 6888942 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #19