Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.8446. Min Act: -0.1700
Data Index: 4851501 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.3446. Min Act: -0.1700
Data Index: 4288781 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.2821. Min Act: -0.1700
Data Index: 8565464 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.2196. Min Act: -0.1700
Data Index: 7547653 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.2196. Min Act: -0.1700
Data Index: 7506138 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.2196. Min Act: -0.1700
Data Index: 4995493 (Open Web Text)
Max Activating Token Index: 345
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.1571. Min Act: -0.1700
Data Index: 317952 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.0946. Min Act: -0.1700
Data Index: 1128775 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 929931 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 1009641 (Open Web Text)
Max Activating Token Index: 600
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.0321. Min Act: -0.1700
Data Index: 8659845 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.0008. Min Act: -0.1700
Data Index: 6495797 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.9696. Min Act: -0.1700
Data Index: 3557901 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.8446. Min Range: -8.8446
Max Act: 8.0008. Min Act: -0.1700
Data Index: 1723162 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.9071. Min Act: -0.1700
Data Index: 685591 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.9071. Min Act: -0.1700
Data Index: 8376226 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.8758. Min Act: -0.1700
Data Index: 850723 (Open Web Text)
Max Activating Token Index: 925
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.8758. Min Act: -0.1700
Data Index: 4039347 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.8758. Min Act: -0.1700
Data Index: 2840628 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.8446. Min Range: -8.8446
Max Act: 7.8758. Min Act: -0.1700
Data Index: 1107502 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #19