Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1766 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1895. Min Range: -8.1895
Max Act: 8.1895. Min Act: -0.1700
Data Index: 7478692 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1895. Min Range: -8.1895
Max Act: 8.0645. Min Act: -0.1700
Data Index: 3081410 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1895. Min Range: -8.1895
Max Act: 8.0645. Min Act: -0.1700
Data Index: 4568662 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1895. Min Range: -8.1895
Max Act: 8.0020. Min Act: -0.1700
Data Index: 3880889 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.9395. Min Act: -0.1700
Data Index: 8151570 (Open Web Text)
Max Activating Token Index: 300
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8770. Min Act: -0.1700
Data Index: 6991676 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8770. Min Act: -0.1700
Data Index: 1794786 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8770. Min Act: -0.1700
Data Index: 7887975 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8770. Min Act: -0.1700
Data Index: 8804555 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8770. Min Act: -0.1700
Data Index: 95587 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8145. Min Act: -0.1700
Data Index: 2182591 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.8145. Min Act: -0.1700
Data Index: 801385 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.7520. Min Act: -0.1700
Data Index: 2503387 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6895. Min Act: -0.1700
Data Index: 5671710 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6895. Min Act: -0.1700
Data Index: 1843140 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6895. Min Act: -0.1700
Data Index: 1653033 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6895. Min Act: -0.1700
Data Index: 6369039 (Open Web Text)
Max Activating Token Index: 424
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6270. Min Act: -0.1700
Data Index: 4326457 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6895. Min Act: -0.1700
Data Index: 3012384 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1895. Min Range: -8.1895
Max Act: 7.6270. Min Act: -0.1700
Data Index: 6678480 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #19