Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6064 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.5690. Min Act: -0.1700
Data Index: 5719213 (Open Web Text)
Max Activating Token Index: 560
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.4753. Min Act: -0.1700
Data Index: 4152222 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.2878. Min Act: -0.1700
Data Index: 6170591 (Open Web Text)
Max Activating Token Index: 809
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.2565. Min Act: -0.1700
Data Index: 1341697 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.2565. Min Act: -0.1700
Data Index: 2510492 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.1940. Min Act: -0.1700
Data Index: 8529841 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.1940. Min Act: -0.1700
Data Index: 8027917 (Open Web Text)
Max Activating Token Index: 420
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.1940. Min Act: -0.1700
Data Index: 5066438 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.1940. Min Act: -0.1700
Data Index: 4239455 (Open Web Text)
Max Activating Token Index: 994
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.1628. Min Act: -0.1700
Data Index: 6733508 (Open Web Text)
Max Activating Token Index: 540
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.1003. Min Act: -0.1700
Data Index: 4798405 (Open Web Text)
Max Activating Token Index: 441
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0378. Min Act: -0.1700
Data Index: 1259306 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0690. Min Act: -0.1700
Data Index: 248880 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0690. Min Act: -0.1700
Data Index: 149530 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0378. Min Act: -0.1700
Data Index: 2433945 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0378. Min Act: -0.1700
Data Index: 993902 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0378. Min Act: -0.1700
Data Index: 1964622 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5690. Min Range: -7.5690
Max Act: 7.0065. Min Act: -0.1700
Data Index: 2602375 (Open Web Text)
Max Activating Token Index: 534
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5690. Min Range: -7.5690
Max Act: 6.9753. Min Act: -0.1700
Data Index: 6096651 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5690. Min Range: -7.5690
Max Act: 6.9753. Min Act: -0.1700
Data Index: 7454318 (Open Web Text)
Max Activating Token Index: 75
Click toggle to see full text
Truncated
Full Text #19