Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3544 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.6404. Min Act: -0.1700
Data Index: 5763846 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.6404. Min Act: -0.1700
Data Index: 6381581 (Open Web Text)
Max Activating Token Index: 621
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.6092. Min Act: -0.1700
Data Index: 8294372 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.5154. Min Act: -0.1700
Data Index: 3026797 (Open Web Text)
Max Activating Token Index: 763
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.5154. Min Act: -0.1700
Data Index: 4778827 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.5467. Min Act: -0.1700
Data Index: 5499735 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.3904. Min Act: -0.1700
Data Index: 5499736 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.4217. Min Act: -0.1700
Data Index: 2843892 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.4529. Min Act: -0.1700
Data Index: 6018585 (Open Web Text)
Max Activating Token Index: 681
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.3904. Min Act: -0.1700
Data Index: 3026788 (Open Web Text)
Max Activating Token Index: 1000
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.3592. Min Act: -0.1700
Data Index: 3680054 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.3279. Min Act: -0.1700
Data Index: 3026796 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2967. Min Act: -0.1700
Data Index: 5543342 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2967. Min Act: -0.1700
Data Index: 2312849 (Open Web Text)
Max Activating Token Index: 737
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2967. Min Act: -0.1700
Data Index: 6378940 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2342. Min Act: -0.1700
Data Index: 6251647 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2654. Min Act: -0.1700
Data Index: 7725047 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.1717. Min Act: -0.1700
Data Index: 5763845 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2029. Min Act: -0.1700
Data Index: 841924 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.6404. Min Range: -6.6404
Max Act: 6.2342. Min Act: -0.1700
Data Index: 3096968 (Open Web Text)
Max Activating Token Index: 498
Click toggle to see full text
Truncated
Full Text #19