Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3164 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.2012. Min Range: -6.2012
Max Act: 6.2012. Min Act: -0.1700
Data Index: 2488010 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.9512. Min Act: -0.1700
Data Index: 8554737 (Open Web Text)
Max Activating Token Index: 836
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6699. Min Act: -0.1700
Data Index: 853866 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6699. Min Act: -0.1700
Data Index: 6108633 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6387. Min Act: -0.1700
Data Index: 3629019 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6387. Min Act: -0.1700
Data Index: 6718806 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6387. Min Act: -0.1700
Data Index: 8554736 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5762. Min Act: -0.1700
Data Index: 118118 (Open Web Text)
Max Activating Token Index: 390
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6074. Min Act: -0.1700
Data Index: 8219476 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.6074. Min Act: -0.1700
Data Index: 6030993 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5762. Min Act: -0.1700
Data Index: 6169865 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5762. Min Act: -0.1700
Data Index: 934380 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5449. Min Act: -0.1700
Data Index: 7201571 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5449. Min Act: -0.1700
Data Index: 5828396 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5449. Min Act: -0.1700
Data Index: 330341 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5137. Min Act: -0.1700
Data Index: 2372388 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5449. Min Act: -0.1700
Data Index: 3193909 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5449. Min Act: -0.1700
Data Index: 1177438 (Open Web Text)
Max Activating Token Index: 843
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.5449. Min Act: -0.1700
Data Index: 5936492 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.2012. Min Range: -6.2012
Max Act: 5.4824. Min Act: -0.1700
Data Index: 7896658 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #19