Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2656 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.4926. Min Act: -0.1700
Data Index: 8794870 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.4301. Min Act: -0.1699
Data Index: 3060070 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.4301. Min Act: -0.1700
Data Index: 1546430 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3676. Min Act: -0.1700
Data Index: 685641 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3676. Min Act: -0.1696
Data Index: 5879211 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3676. Min Act: -0.1700
Data Index: 8604728 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3676. Min Act: -0.1700
Data Index: 7379949 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 3586573 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1697
Data Index: 5260917 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 2375547 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 7701388 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 7390043 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 6695440 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 5902312 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1698
Data Index: 1098543 (Open Web Text)
Max Activating Token Index: 9
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1691
Data Index: 5623639 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1700
Data Index: 674197 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.3051. Min Act: -0.1698
Data Index: 654475 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.2426. Min Act: -0.1692
Data Index: 3447746 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.4926. Min Range: -7.4926
Max Act: 7.2426. Min Act: -0.1699
Data Index: 3518219 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19