Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2939 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.2014. Min Act: -0.1700
Data Index: 7049285 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.1701. Min Act: -0.1700
Data Index: 137606 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.1076. Min Act: -0.1700
Data Index: 4743616 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0764. Min Act: -0.1700
Data Index: 5956976 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0138. Min Act: -0.1700
Data Index: 7337099 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0451. Min Act: -0.1700
Data Index: 7278505 (Open Web Text)
Max Activating Token Index: 166
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0451. Min Act: -0.1700
Data Index: 1770983 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0764. Min Act: -0.1700
Data Index: 3349500 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0138. Min Act: -0.1700
Data Index: 7019978 (Open Web Text)
Max Activating Token Index: 50
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2014. Min Range: -4.2014
Max Act: 4.0138. Min Act: -0.1700
Data Index: 1838573 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9826. Min Act: -0.1700
Data Index: 5134772 (Open Web Text)
Max Activating Token Index: 256
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9826. Min Act: -0.1700
Data Index: 1183810 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9513. Min Act: -0.1700
Data Index: 4861247 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9200. Min Act: -0.1700
Data Index: 5904214 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9513. Min Act: -0.1700
Data Index: 3374146 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9513. Min Act: -0.1700
Data Index: 7242495 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9200. Min Act: -0.1700
Data Index: 3376301 (Open Web Text)
Max Activating Token Index: 114
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9200. Min Act: -0.1700
Data Index: 4694348 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.9200. Min Act: -0.1700
Data Index: 5758196 (Open Web Text)
Max Activating Token Index: 31
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2014. Min Range: -4.2014
Max Act: 3.8888. Min Act: -0.1700
Data Index: 5979405 (Open Web Text)
Max Activating Token Index: 99
Click toggle to see full text
Truncated
Full Text #19