Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2628 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3851. Min Range: -5.3851
Max Act: 5.3851. Min Act: -0.1700
Data Index: 2226482 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3851. Min Range: -5.3851
Max Act: 5.1976. Min Act: -0.1700
Data Index: 2212607 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3851. Min Range: -5.3851
Max Act: 5.1976. Min Act: -0.1700
Data Index: 1148875 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3851. Min Range: -5.3851
Max Act: 5.0726. Min Act: -0.1700
Data Index: 2971047 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3851. Min Range: -5.3851
Max Act: 5.1038. Min Act: -0.1700
Data Index: 1118451 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3851. Min Range: -5.3851
Max Act: 5.0101. Min Act: -0.1700
Data Index: 2691344 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.9788. Min Act: -0.1700
Data Index: 7902612 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.9788. Min Act: -0.1700
Data Index: 2333592 (Open Web Text)
Max Activating Token Index: 951
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.9788. Min Act: -0.1700
Data Index: 2310295 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.9476. Min Act: -0.1700
Data Index: 7789764 (Open Web Text)
Max Activating Token Index: 478
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.9476. Min Act: -0.1700
Data Index: 5013978 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.9163. Min Act: -0.1700
Data Index: 5476046 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 4346585 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 5331561 (Open Web Text)
Max Activating Token Index: 201
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 616855 (Open Web Text)
Max Activating Token Index: 782
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 118401 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8538. Min Act: -0.1700
Data Index: 4087796 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 4275442 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8851. Min Act: -0.1700
Data Index: 7411111 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3851. Min Range: -5.3851
Max Act: 4.8538. Min Act: -0.1700
Data Index: 4108917 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #19