Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2562 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1698. Min Range: -5.1698
Max Act: 5.1698. Min Act: -0.1700
Data Index: 506497 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1698. Min Range: -5.1698
Max Act: 5.0448. Min Act: -0.1700
Data Index: 2646908 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1698. Min Range: -5.1698
Max Act: 5.0448. Min Act: -0.1700
Data Index: 1817846 (Open Web Text)
Max Activating Token Index: 570
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1698. Min Range: -5.1698
Max Act: 5.0136. Min Act: -0.1700
Data Index: 2452570 (Open Web Text)
Max Activating Token Index: 143
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1698. Min Range: -5.1698
Max Act: 5.0448. Min Act: -0.1700
Data Index: 8593954 (Open Web Text)
Max Activating Token Index: 325
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.7323. Min Act: -0.1700
Data Index: 399778 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.7323. Min Act: -0.1700
Data Index: 719143 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.7636. Min Act: -0.1700
Data Index: 5395254 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6698. Min Act: -0.1700
Data Index: 6216282 (Open Web Text)
Max Activating Token Index: 133
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.7011. Min Act: -0.1700
Data Index: 2766557 (Open Web Text)
Max Activating Token Index: 841
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6698. Min Act: -0.1700
Data Index: 5658679 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6386. Min Act: -0.1700
Data Index: 4624091 (Open Web Text)
Max Activating Token Index: 353
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6386. Min Act: -0.1700
Data Index: 1883536 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6073. Min Act: -0.1700
Data Index: 8352705 (Open Web Text)
Max Activating Token Index: 403
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6073. Min Act: -0.1700
Data Index: 6686193 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6073. Min Act: -0.1700
Data Index: 4951702 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.5761. Min Act: -0.1700
Data Index: 991800 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.6073. Min Act: -0.1700
Data Index: 6024824 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.5761. Min Act: -0.1700
Data Index: 4907004 (Open Web Text)
Max Activating Token Index: 110
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1698. Min Range: -5.1698
Max Act: 4.5761. Min Act: -0.1700
Data Index: 4509106 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19