Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4346 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.9474. Min Act: -0.1700
Data Index: 2394572 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.4162. Min Act: -0.1700
Data Index: 350103 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.3537. Min Act: -0.1700
Data Index: 5718082 (Open Web Text)
Max Activating Token Index: 106
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.2912. Min Act: -0.1700
Data Index: 8441131 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.2912. Min Act: -0.1700
Data Index: 5192686 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.1974. Min Act: -0.1700
Data Index: 1453474 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.1974. Min Act: -0.1700
Data Index: 437946 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.1662. Min Act: -0.1700
Data Index: 5260384 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.1662. Min Act: -0.1700
Data Index: 3282935 (Open Web Text)
Max Activating Token Index: 311
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.1349. Min Act: -0.1700
Data Index: 473464 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.0724. Min Act: -0.1700
Data Index: 6163570 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.0412. Min Act: -0.1700
Data Index: 7487509 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.0412. Min Act: -0.1700
Data Index: 4787882 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9474. Min Range: -6.9474
Max Act: 6.0099. Min Act: -0.1700
Data Index: 3452808 (Open Web Text)
Max Activating Token Index: 581
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9474. Min Range: -6.9474
Max Act: 5.9787. Min Act: -0.1700
Data Index: 1707132 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9474. Min Range: -6.9474
Max Act: 5.9474. Min Act: -0.1700
Data Index: 8651719 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9474. Min Range: -6.9474
Max Act: 5.9787. Min Act: -0.1700
Data Index: 8799744 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9474. Min Range: -6.9474
Max Act: 5.9474. Min Act: -0.1700
Data Index: 2624147 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9474. Min Range: -6.9474
Max Act: 5.9474. Min Act: -0.1700
Data Index: 1037146 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9474. Min Range: -6.9474
Max Act: 5.9474. Min Act: -0.1700
Data Index: 1723263 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #19