Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3187 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.5633. Min Act: -0.1700
Data Index: 344975 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.3133. Min Act: -0.1700
Data Index: 6340448 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2821. Min Act: -0.1700
Data Index: 911432 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2821. Min Act: -0.1700
Data Index: 4334510 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2508. Min Act: -0.1700
Data Index: 3543558 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2508. Min Act: -0.1700
Data Index: 344978 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2821. Min Act: -0.1700
Data Index: 1747932 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2196. Min Act: -0.1700
Data Index: 407543 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.2196. Min Act: -0.1700
Data Index: 7393992 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.1571. Min Act: -0.1700
Data Index: 2418027 (Open Web Text)
Max Activating Token Index: 578
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.1571. Min Act: -0.1700
Data Index: 1453160 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.1258. Min Act: -0.1700
Data Index: 5158729 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0946. Min Act: -0.1700
Data Index: 10152 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0946. Min Act: -0.1700
Data Index: 2211296 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0633. Min Act: -0.1700
Data Index: 6211969 (Open Web Text)
Max Activating Token Index: 893
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0633. Min Act: -0.1700
Data Index: 8598907 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0321. Min Act: -0.1700
Data Index: 8378786 (Open Web Text)
Max Activating Token Index: 703
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0321. Min Act: -0.1700
Data Index: 6117164 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0321. Min Act: -0.1700
Data Index: 6220567 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5633. Min Range: -5.5633
Max Act: 5.0321. Min Act: -0.1700
Data Index: 8128656 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #19