Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3098 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.4557. Min Act: -0.1700
Data Index: 2689086 (Open Web Text)
Max Activating Token Index: 221
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.2057. Min Act: -0.1700
Data Index: 4966003 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.1119. Min Act: -0.1700
Data Index: 690294 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.0807. Min Act: -0.1700
Data Index: 8258049 (Open Web Text)
Max Activating Token Index: 82
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.1432. Min Act: -0.1700
Data Index: 1577656 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.0807. Min Act: -0.1700
Data Index: 5008431 (Open Web Text)
Max Activating Token Index: 694
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.0807. Min Act: -0.1700
Data Index: 7548900 (Open Web Text)
Max Activating Token Index: 77
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.0182. Min Act: -0.1700
Data Index: 4132475 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.0182. Min Act: -0.1700
Data Index: 3201876 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4557. Min Range: -6.4557
Max Act: 6.0494. Min Act: -0.1700
Data Index: 7748363 (Open Web Text)
Max Activating Token Index: 518
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9869. Min Act: -0.1700
Data Index: 7723204 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9557. Min Act: -0.1700
Data Index: 8095160 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9557. Min Act: -0.1700
Data Index: 3146877 (Open Web Text)
Max Activating Token Index: 977
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9557. Min Act: -0.1700
Data Index: 2807431 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9557. Min Act: -0.1700
Data Index: 2617518 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9557. Min Act: -0.1700
Data Index: 4247018 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9244. Min Act: -0.1700
Data Index: 6807589 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.9244. Min Act: -0.1700
Data Index: 5366165 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.8932. Min Act: -0.1700
Data Index: 578931 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4557. Min Range: -6.4557
Max Act: 5.8932. Min Act: -0.1700
Data Index: 7657783 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #19