Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3473 in Layer 37
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.4530. Min Act: -0.1700
Data Index: 8755093 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.2968. Min Act: -0.1700
Data Index: 5805878 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.2968. Min Act: -0.1700
Data Index: 552756 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.2655. Min Act: -0.1700
Data Index: 1466546 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.2030. Min Act: -0.1700
Data Index: 216415 (Open Web Text)
Max Activating Token Index: 895
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 6224138 (Open Web Text)
Max Activating Token Index: 730
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5262791 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5748938 (Open Web Text)
Max Activating Token Index: 430
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 5618813 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 1445100 (Open Web Text)
Max Activating Token Index: 789
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 7484647 (Open Web Text)
Max Activating Token Index: 505
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1405. Min Act: -0.1700
Data Index: 6176257 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1718. Min Act: -0.1700
Data Index: 670576 (Open Web Text)
Max Activating Token Index: 993
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1405. Min Act: -0.1700
Data Index: 2227077 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1093. Min Act: -0.1700
Data Index: 3320914 (Open Web Text)
Max Activating Token Index: 384
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.0780. Min Act: -0.1700
Data Index: 5911450 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1093. Min Act: -0.1700
Data Index: 8676517 (Open Web Text)
Max Activating Token Index: 556
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.0780. Min Act: -0.1700
Data Index: 5387867 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.1093. Min Act: -0.1700
Data Index: 4516145 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4530. Min Range: -5.4530
Max Act: 5.0780. Min Act: -0.1700
Data Index: 2826233 (Open Web Text)
Max Activating Token Index: 530
Click toggle to see full text
Truncated
Full Text #19