Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 72 in Layer 21
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 7.2047. Min Range: -7.2047
Max Act: 7.2047. Min Act: -0.1700
Data Index: 3093860 (Open Web Text)
Max Activating Token Index: 313
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.8922. Min Act: -0.1700
Data Index: 4649365 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.8922. Min Act: -0.1700
Data Index: 1617084 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.8922. Min Act: -0.1700
Data Index: 5422691 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.8609. Min Act: -0.1700
Data Index: 1465397 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.8609. Min Act: -0.1700
Data Index: 3262739 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7984. Min Act: -0.1700
Data Index: 7321167 (Open Web Text)
Max Activating Token Index: 616
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7672. Min Act: -0.1700
Data Index: 8232182 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7359. Min Act: -0.1700
Data Index: 8515051 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7672. Min Act: -0.1700
Data Index: 2412926 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7047. Min Act: -0.1700
Data Index: 4004427 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7047. Min Act: -0.1700
Data Index: 6139334 (Open Web Text)
Max Activating Token Index: 990
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6734. Min Act: -0.1700
Data Index: 1537501 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.7047. Min Act: -0.1700
Data Index: 5488318 (Open Web Text)
Max Activating Token Index: 312
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6422. Min Act: -0.1700
Data Index: 8446765 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6422. Min Act: -0.1700
Data Index: 5973198 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6422. Min Act: -0.1700
Data Index: 47942 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6734. Min Act: -0.1700
Data Index: 6861039 (Open Web Text)
Max Activating Token Index: 499
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6422. Min Act: -0.1700
Data Index: 2063349 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2047. Min Range: -7.2047
Max Act: 6.6109. Min Act: -0.1700
Data Index: 4041774 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #19