Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5858 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1611. Min Range: -8.1611
Max Act: 8.1611. Min Act: -0.1700
Data Index: 8558626 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.8173. Min Act: -0.1700
Data Index: 6750026 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.7236. Min Act: -0.1700
Data Index: 2869078 (Open Web Text)
Max Activating Token Index: 552
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.7236. Min Act: -0.1700
Data Index: 6159582 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.6923. Min Act: -0.1700
Data Index: 706185 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.6923. Min Act: -0.1700
Data Index: 3375310 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.6611. Min Act: -0.1700
Data Index: 1176384 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.6298. Min Act: -0.1700
Data Index: 6211911 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.5986. Min Act: -0.1700
Data Index: 1444254 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.5361. Min Act: -0.1700
Data Index: 5813898 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.5361. Min Act: -0.1700
Data Index: 5188684 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.5361. Min Act: -0.1700
Data Index: 571364 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.5048. Min Act: -0.1700
Data Index: 1361655 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.4736. Min Act: -0.1700
Data Index: 5494060 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.4423. Min Act: -0.1700
Data Index: 2008377 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.4423. Min Act: -0.1700
Data Index: 6842230 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.4423. Min Act: -0.1700
Data Index: 2895285 (Open Web Text)
Max Activating Token Index: 160
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.4423. Min Act: -0.1700
Data Index: 8790813 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.4111. Min Act: -0.1700
Data Index: 5608230 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1611. Min Range: -8.1611
Max Act: 7.3798. Min Act: -0.1700
Data Index: 4693798 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #19