Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6163 in Layer 26
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.3735. Min Act: -0.1700
Data Index: 4150958 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.3110. Min Act: -0.1700
Data Index: 1113926 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3735. Min Range: -5.3735
Max Act: 5.2173. Min Act: -0.1700
Data Index: 850766 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.9985. Min Act: -0.1700
Data Index: 2472516 (Open Web Text)
Max Activating Token Index: 812
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.9048. Min Act: -0.1700
Data Index: 3115665 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.8423. Min Act: -0.1700
Data Index: 488298 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7798. Min Act: -0.1700
Data Index: 4288765 (Open Web Text)
Max Activating Token Index: 818
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7798. Min Act: -0.1700
Data Index: 4124125 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7798. Min Act: -0.1700
Data Index: 2027076 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7485. Min Act: -0.1700
Data Index: 2916619 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7485. Min Act: -0.1700
Data Index: 4651509 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7485. Min Act: -0.1700
Data Index: 239783 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7173. Min Act: -0.1700
Data Index: 5240831 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.7485. Min Act: -0.1700
Data Index: 5731663 (Open Web Text)
Max Activating Token Index: 373
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.6860. Min Act: -0.1700
Data Index: 258696 (Open Web Text)
Max Activating Token Index: 796
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.6548. Min Act: -0.1700
Data Index: 5524610 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.6548. Min Act: -0.1700
Data Index: 3260150 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.6548. Min Act: -0.1700
Data Index: 130340 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.6860. Min Act: -0.1700
Data Index: 1750035 (Open Web Text)
Max Activating Token Index: 362
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3735. Min Range: -5.3735
Max Act: 4.6548. Min Act: -0.1700
Data Index: 1752234 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #19