Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2980 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.9821. Min Act: -0.1700
Data Index: 4523870 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.9196. Min Act: -0.1700
Data Index: 8619756 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.9196. Min Act: -0.1700
Data Index: 1834440 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8727. Min Act: -0.1700
Data Index: 3595327 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8883. Min Act: -0.1700
Data Index: 1515646 (Open Web Text)
Max Activating Token Index: 100
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8727. Min Act: -0.1700
Data Index: 85185 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8727. Min Act: -0.1700
Data Index: 2051139 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8727. Min Act: -0.1700
Data Index: 4207845 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8727. Min Act: -0.1700
Data Index: 5120697 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8414. Min Act: -0.1700
Data Index: 6669953 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.8101. Min Act: -0.1700
Data Index: 1083306 (Open Web Text)
Max Activating Token Index: 150
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7789. Min Act: -0.1700
Data Index: 6312640 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7789. Min Act: -0.1700
Data Index: 3003751 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 7194786 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 8775082 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7476. Min Act: -0.1700
Data Index: 4694381 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 6023169 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 3700256 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7789. Min Act: -0.1700
Data Index: 6991549 (Open Web Text)
Max Activating Token Index: 304
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9821. Min Range: -3.9821
Max Act: 3.7632. Min Act: -0.1700
Data Index: 54020 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #19