Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4550 in Layer 14
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.3706. Min Act: -0.1700
Data Index: 547458 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.1831. Min Act: -0.1700
Data Index: 5000460 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.1831. Min Act: -0.1700
Data Index: 2732075 (Open Web Text)
Max Activating Token Index: 991
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.1206. Min Act: -0.1700
Data Index: 4737821 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.0581. Min Act: -0.1700
Data Index: 2577693 (Open Web Text)
Max Activating Token Index: 638
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.1206. Min Act: -0.1700
Data Index: 3320226 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3706. Min Range: -8.3706
Max Act: 8.0581. Min Act: -0.1700
Data Index: 6623739 (Open Web Text)
Max Activating Token Index: 881
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.9956. Min Act: -0.1700
Data Index: 7583680 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.9956. Min Act: -0.1700
Data Index: 7238455 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.9331. Min Act: -0.1700
Data Index: 8377867 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.9331. Min Act: -0.1700
Data Index: 3589798 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.9956. Min Act: -0.1700
Data Index: 1445002 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.8706. Min Act: -0.1700
Data Index: 7074721 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.8706. Min Act: -0.1700
Data Index: 654470 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.8706. Min Act: -0.1700
Data Index: 923910 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.8081. Min Act: -0.1700
Data Index: 1838798 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.7456. Min Act: -0.1700
Data Index: 6780925 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.8081. Min Act: -0.1700
Data Index: 3952767 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.7456. Min Act: -0.1700
Data Index: 7809549 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3706. Min Range: -8.3706
Max Act: 7.8081. Min Act: -0.1700
Data Index: 1163606 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #19