Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 17 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.7536. Min Act: -0.1700
Data Index: 1531927 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.6415. Min Act: -0.1700
Data Index: 1995121 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.5933. Min Act: -0.1700
Data Index: 1556877 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.5611. Min Act: -0.1700
Data Index: 7282048 (Open Web Text)
Max Activating Token Index: 724
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.5611. Min Act: -0.1700
Data Index: 7685261 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.5449. Min Act: -0.1700
Data Index: 1400124 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.5288. Min Act: -0.1700
Data Index: 6879109 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4639. Min Act: -0.1700
Data Index: 7731153 (Open Web Text)
Max Activating Token Index: 727
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4477. Min Act: -0.1700
Data Index: 7248897 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4477. Min Act: -0.1700
Data Index: 1835965 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4639. Min Act: -0.1700
Data Index: 6444786 (Open Web Text)
Max Activating Token Index: 484
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4477. Min Act: -0.1700
Data Index: 958218 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4151. Min Act: -0.1700
Data Index: 1850833 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4151. Min Act: -0.1700
Data Index: 1949935 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4151. Min Act: -0.1700
Data Index: 3068397 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.4151. Min Act: -0.1700
Data Index: 3670106 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.3988. Min Act: -0.1700
Data Index: 1735240 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.3825. Min Act: -0.1700
Data Index: 626516 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.3988. Min Act: -0.1700
Data Index: 6827829 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7536. Min Range: -2.7536
Max Act: 2.3988. Min Act: -0.1700
Data Index: 4021416 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #19