Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1784 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.5089. Min Act: -0.1700
Data Index: 7949 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.3214. Min Act: -0.1700
Data Index: 7373640 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2902. Min Act: -0.1700
Data Index: 7975672 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.2589. Min Act: -0.1700
Data Index: 3348899 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1964. Min Act: -0.1700
Data Index: 5445298 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1652. Min Act: -0.1700
Data Index: 7974097 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1652. Min Act: -0.1700
Data Index: 8335133 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1339. Min Act: -0.1700
Data Index: 6891078 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1027. Min Act: -0.1700
Data Index: 5315483 (Open Web Text)
Max Activating Token Index: 417
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1027. Min Act: -0.1700
Data Index: 3692900 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1027. Min Act: -0.1700
Data Index: 6323047 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0714. Min Act: -0.1700
Data Index: 307371 (Open Web Text)
Max Activating Token Index: 626
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0402. Min Act: -0.1700
Data Index: 4344410 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0714. Min Act: -0.1700
Data Index: 197748 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0714. Min Act: -0.1700
Data Index: 3105569 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0714. Min Act: -0.1700
Data Index: 715390 (Open Web Text)
Max Activating Token Index: 26
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0402. Min Act: -0.1700
Data Index: 1812268 (Open Web Text)
Max Activating Token Index: 944
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.1027. Min Act: -0.1700
Data Index: 4463992 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0714. Min Act: -0.1700
Data Index: 7998396 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5089. Min Range: -6.5089
Max Act: 6.0089. Min Act: -0.1698
Data Index: 5651731 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #19