Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5404 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.6863. Min Act: -0.1700
Data Index: 4557545 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.6238. Min Act: -0.1700
Data Index: 7444544 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.5613. Min Act: -0.1700
Data Index: 1319808 (Open Web Text)
Max Activating Token Index: 805
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.5613. Min Act: -0.1700
Data Index: 1023044 (Open Web Text)
Max Activating Token Index: 801
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.5613. Min Act: -0.1700
Data Index: 5715977 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.5301. Min Act: -0.1700
Data Index: 5715971 (Open Web Text)
Max Activating Token Index: 984
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4988. Min Act: -0.1700
Data Index: 7101996 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4988. Min Act: -0.1700
Data Index: 5715975 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4988. Min Act: -0.1700
Data Index: 2762082 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4988. Min Act: -0.1700
Data Index: 653208 (Open Web Text)
Max Activating Token Index: 713
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4676. Min Act: -0.1700
Data Index: 1023054 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4363. Min Act: -0.1700
Data Index: 1023055 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4363. Min Act: -0.1700
Data Index: 4557544 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4051. Min Act: -0.1700
Data Index: 6594686 (Open Web Text)
Max Activating Token Index: 873
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.4051. Min Act: -0.1700
Data Index: 4793815 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.3738. Min Act: -0.1700
Data Index: 1818871 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.3738. Min Act: -0.1700
Data Index: 7347916 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.3738. Min Act: -0.1700
Data Index: 5715976 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.3426. Min Act: -0.1700
Data Index: 1719117 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6863. Min Range: -6.6863
Max Act: 6.3738. Min Act: -0.1700
Data Index: 4853386 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #19