Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2686 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7342. Min Act: -0.1700
Data Index: 3349694 (Open Web Text)
Max Activating Token Index: 467
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7342. Min Act: -0.1700
Data Index: 2147770 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7030. Min Act: -0.1700
Data Index: 6015683 (Open Web Text)
Max Activating Token Index: 791
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7030. Min Act: -0.1700
Data Index: 4699202 (Open Web Text)
Max Activating Token Index: 409
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7030. Min Act: -0.1700
Data Index: 6824259 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7030. Min Act: -0.1700
Data Index: 6245070 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.7030. Min Act: -0.1700
Data Index: 5354816 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.6717. Min Act: -0.1700
Data Index: 2147771 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.6717. Min Act: -0.1700
Data Index: 5744553 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.6717. Min Act: -0.1700
Data Index: 6015684 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.6405. Min Act: -0.1700
Data Index: 7875963 (Open Web Text)
Max Activating Token Index: 717
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.6092. Min Act: -0.1700
Data Index: 6070034 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.5467. Min Act: -0.1700
Data Index: 6290764 (Open Web Text)
Max Activating Token Index: 207
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.5155. Min Act: -0.1700
Data Index: 5900866 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.5155. Min Act: -0.1700
Data Index: 6208791 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.5155. Min Act: -0.1700
Data Index: 1175244 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.5467. Min Act: -0.1700
Data Index: 5744554 (Open Web Text)
Max Activating Token Index: 265
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.4530. Min Act: -0.1700
Data Index: 6262894 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.4842. Min Act: -0.1700
Data Index: 3002226 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7342. Min Range: -6.7342
Max Act: 6.5155. Min Act: -0.1700
Data Index: 6824260 (Open Web Text)
Max Activating Token Index: 156
Click toggle to see full text
Truncated
Full Text #19