Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2821 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.3635. Min Act: -0.1700
Data Index: 334335 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.2698. Min Act: -0.1700
Data Index: 3194933 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.1760. Min Act: -0.1700
Data Index: 8081147 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.1448. Min Act: -0.1700
Data Index: 2170016 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.0823. Min Act: -0.1700
Data Index: 6096481 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.0823. Min Act: -0.1700
Data Index: 4396078 (Open Web Text)
Max Activating Token Index: 185
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.3635. Min Range: -5.3635
Max Act: 5.0510. Min Act: -0.1700
Data Index: 712093 (Open Web Text)
Max Activating Token Index: 423
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.9260. Min Act: -0.1700
Data Index: 5225496 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.8948. Min Act: -0.1700
Data Index: 3145121 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.8635. Min Act: -0.1700
Data Index: 1709966 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.8323. Min Act: -0.1700
Data Index: 724145 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7698. Min Act: -0.1700
Data Index: 5222114 (Open Web Text)
Max Activating Token Index: 248
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7698. Min Act: -0.1700
Data Index: 4435785 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7385. Min Act: -0.1700
Data Index: 7727334 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7385. Min Act: -0.1700
Data Index: 4276041 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7073. Min Act: -0.1700
Data Index: 4046957 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7073. Min Act: -0.1700
Data Index: 1606901 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7073. Min Act: -0.1700
Data Index: 7469749 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7073. Min Act: -0.1700
Data Index: 4338774 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.3635. Min Range: -5.3635
Max Act: 4.7073. Min Act: -0.1700
Data Index: 545060 (Open Web Text)
Max Activating Token Index: 333
Click toggle to see full text
Truncated
Full Text #19