Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3653 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.1025. Min Range: -8.1025
Max Act: 8.1025. Min Act: -0.1700
Data Index: 3875487 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.1025. Min Range: -8.1025
Max Act: 8.0400. Min Act: -0.1700
Data Index: 8098950 (Open Web Text)
Max Activating Token Index: 615
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.6025. Min Act: -0.1700
Data Index: 5923592 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.5713. Min Act: -0.1700
Data Index: 7571105 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.5400. Min Act: -0.1700
Data Index: 4360975 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.5088. Min Act: -0.1700
Data Index: 3750783 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.4463. Min Act: -0.1700
Data Index: 4361331 (Open Web Text)
Max Activating Token Index: 975
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.3838. Min Act: -0.1700
Data Index: 5276892 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.2588. Min Act: -0.1700
Data Index: 686549 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1650. Min Act: -0.1700
Data Index: 7642159 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1963. Min Act: -0.1700
Data Index: 17583 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1338. Min Act: -0.1700
Data Index: 7329479 (Open Web Text)
Max Activating Token Index: 39
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1650. Min Act: -0.1700
Data Index: 3450446 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1338. Min Act: -0.1700
Data Index: 2535598 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1338. Min Act: -0.1700
Data Index: 6504586 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1338. Min Act: -0.1700
Data Index: 2602493 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.1025. Min Act: -0.1700
Data Index: 7409652 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.0713. Min Act: -0.1700
Data Index: 2768411 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.0400. Min Act: -0.1700
Data Index: 5413944 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.1025. Min Range: -8.1025
Max Act: 7.0713. Min Act: -0.1700
Data Index: 4547144 (Open Web Text)
Max Activating Token Index: 946
Click toggle to see full text
Truncated
Full Text #19