Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3579 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.4440. Min Act: -0.1700
Data Index: 3948874 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.4440. Min Act: -0.1700
Data Index: 2567386 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.3815. Min Act: -0.1700
Data Index: 5354005 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.3190. Min Act: -0.1700
Data Index: 8088383 (Open Web Text)
Max Activating Token Index: 831
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.1315. Min Act: -0.1700
Data Index: 5289757 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.1940. Min Act: -0.1700
Data Index: 4572578 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.1315. Min Act: -0.1700
Data Index: 3948864 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.1315. Min Act: -0.1700
Data Index: 674466 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.0690. Min Act: -0.1700
Data Index: 5896172 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.0690. Min Act: -0.1700
Data Index: 4891 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.8815. Min Act: -0.1700
Data Index: 5137132 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.0065. Min Act: -0.1700
Data Index: 4890 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.9440. Min Act: -0.1700
Data Index: 7488988 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.9440. Min Act: -0.1700
Data Index: 998364 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.9440. Min Act: -0.1700
Data Index: 6767018 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.9440. Min Act: -0.1700
Data Index: 4846680 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 10.4440. Min Range: -10.4440
Max Act: 10.0065. Min Act: -0.1700
Data Index: 7250837 (Open Web Text)
Max Activating Token Index: 1011
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.8815. Min Act: -0.1700
Data Index: 7198894 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.9440. Min Act: -0.1699
Data Index: 109917 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 10.4440. Min Range: -10.4440
Max Act: 9.8815. Min Act: -0.1700
Data Index: 3900175 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #19