Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2021 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0478. Min Range: -6.0478
Max Act: 6.0478. Min Act: -0.1700
Data Index: 7048268 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0478. Min Range: -6.0478
Max Act: 6.0165. Min Act: -0.1700
Data Index: 7161614 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.9540. Min Act: -0.1700
Data Index: 3495310 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.8915. Min Act: -0.1700
Data Index: 7180480 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.7978. Min Act: -0.1700
Data Index: 8028949 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.7978. Min Act: -0.1700
Data Index: 1301251 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.7665. Min Act: -0.1700
Data Index: 6643466 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.7665. Min Act: -0.1700
Data Index: 5781758 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6728. Min Act: -0.1700
Data Index: 7424363 (Open Web Text)
Max Activating Token Index: 1009
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.7040. Min Act: -0.1700
Data Index: 4949695 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6728. Min Act: -0.1700
Data Index: 2798108 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6728. Min Act: -0.1700
Data Index: 4383872 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 7426072 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6415. Min Act: -0.1700
Data Index: 3338105 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6415. Min Act: -0.1700
Data Index: 7030417 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6415. Min Act: -0.1700
Data Index: 38666 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6415. Min Act: -0.1700
Data Index: 57755 (Open Web Text)
Max Activating Token Index: 526
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6415. Min Act: -0.1700
Data Index: 57504 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 1740202 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0478. Min Range: -6.0478
Max Act: 5.6103. Min Act: -0.1700
Data Index: 5500763 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #19