Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2007 in Layer 44
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3490. Min Range: -8.3490
Max Act: 8.3490. Min Act: -0.1700
Data Index: 5386924 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3490. Min Range: -8.3490
Max Act: 8.0990. Min Act: -0.1700
Data Index: 2510891 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3490. Min Range: -8.3490
Max Act: 8.0990. Min Act: -0.1700
Data Index: 437513 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3490. Min Range: -8.3490
Max Act: 8.0365. Min Act: -0.1700
Data Index: 7691090 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.9740. Min Act: -0.1700
Data Index: 5617470 (Open Web Text)
Max Activating Token Index: 317
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3490. Min Range: -8.3490
Max Act: 8.0365. Min Act: -0.1700
Data Index: 304646 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.9740. Min Act: -0.1700
Data Index: 4479026 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8803. Min Act: -0.1700
Data Index: 5132059 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8803. Min Act: -0.1700
Data Index: 2344727 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8490. Min Act: -0.1700
Data Index: 1239678 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8178. Min Act: -0.1700
Data Index: 5754510 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8490. Min Act: -0.1700
Data Index: 938637 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8178. Min Act: -0.1700
Data Index: 758019 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8490. Min Act: -0.1700
Data Index: 4213567 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8178. Min Act: -0.1700
Data Index: 5193966 (Open Web Text)
Max Activating Token Index: 919
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.8178. Min Act: -0.1700
Data Index: 6703058 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.7865. Min Act: -0.1700
Data Index: 7872605 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.7553. Min Act: -0.1700
Data Index: 4587918 (Open Web Text)
Max Activating Token Index: 97
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.7553. Min Act: -0.1700
Data Index: 4132303 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3490. Min Range: -8.3490
Max Act: 7.7553. Min Act: -0.1700
Data Index: 1346773 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #19