Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2995 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.8665. Min Range: -9.8665
Max Act: 9.8665. Min Act: -0.1700
Data Index: 2731043 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.8665. Min Range: -9.8665
Max Act: 9.6790. Min Act: -0.1700
Data Index: 882675 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.8665. Min Range: -9.8665
Max Act: 9.6165. Min Act: -0.1700
Data Index: 2731028 (Open Web Text)
Max Activating Token Index: 307
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.8665. Min Range: -9.8665
Max Act: 9.4915. Min Act: -0.1700
Data Index: 2731027 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.8665. Min Range: -9.8665
Max Act: 9.4290. Min Act: -0.1700
Data Index: 2731036 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.8040. Min Act: -0.1700
Data Index: 671070 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.8040. Min Act: -0.1700
Data Index: 2044504 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.7415. Min Act: -0.1700
Data Index: 5388448 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.6790. Min Act: -0.1700
Data Index: 3598954 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.5540. Min Act: -0.1700
Data Index: 2731033 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.5540. Min Act: -0.1700
Data Index: 5388449 (Open Web Text)
Max Activating Token Index: 912
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.4915. Min Act: -0.1700
Data Index: 2044501 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.5540. Min Act: -0.1700
Data Index: 6745039 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.4915. Min Act: -0.1700
Data Index: 7585306 (Open Web Text)
Max Activating Token Index: 509
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.4915. Min Act: -0.1700
Data Index: 3598953 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.3665. Min Act: -0.1700
Data Index: 4329072 (Open Web Text)
Max Activating Token Index: 483
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.4290. Min Act: -0.1700
Data Index: 2731031 (Open Web Text)
Max Activating Token Index: 606
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.3665. Min Act: -0.1700
Data Index: 5537814 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.2415. Min Act: -0.1700
Data Index: 2731037 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.8665. Min Range: -9.8665
Max Act: 8.3040. Min Act: -0.1700
Data Index: 1150211 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #19