Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.7374. Min Act: -0.1700
Data Index: 1066162 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.6560. Min Act: -0.1687
Data Index: 8312787 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.6560. Min Act: -0.1700
Data Index: 6300093 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.6240. Min Act: -0.1700
Data Index: 7980483 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.6240. Min Act: -0.1700
Data Index: 6481064 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.6161. Min Act: -0.1700
Data Index: 7838354 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.6081. Min Act: -0.1699
Data Index: 2719153 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5768. Min Act: -0.1694
Data Index: 7010250 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5768. Min Act: -0.1700
Data Index: 8732290 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5768. Min Act: -0.1696
Data Index: 7099393 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5690. Min Act: -0.1700
Data Index: 7119544 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5690. Min Act: -0.1698
Data Index: 6291064 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5612. Min Act: -0.1679
Data Index: 8025106 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5612. Min Act: -0.1690
Data Index: 3970780 (Open Web Text)
Max Activating Token Index: 617
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5612. Min Act: -0.1694
Data Index: 1040368 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5612. Min Act: -0.1679
Data Index: 446364 (Open Web Text)
Max Activating Token Index: 858
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5535. Min Act: -0.1700
Data Index: 537231 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5535. Min Act: -0.1679
Data Index: 5793391 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5458. Min Act: -0.1700
Data Index: 3895176 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.7374. Min Range: -0.7374
Max Act: 0.5458. Min Act: -0.1698
Data Index: 1752986 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #19