Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 9 in Layer 20
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.9017. Min Act: -0.1700
Data Index: 5395573 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.8704. Min Act: -0.1700
Data Index: 8621467 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.8704. Min Act: -0.1700
Data Index: 21972 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.7767. Min Act: -0.1700
Data Index: 2618066 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.7767. Min Act: -0.1700
Data Index: 2642867 (Open Web Text)
Max Activating Token Index: 586
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.7142. Min Act: -0.1700
Data Index: 4314963 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.7142. Min Act: -0.1700
Data Index: 2588190 (Open Web Text)
Max Activating Token Index: 466
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.7142. Min Act: -0.1700
Data Index: 4039902 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.6204. Min Act: -0.1700
Data Index: 6998643 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.6204. Min Act: -0.1700
Data Index: 6318545 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.6517. Min Act: -0.1700
Data Index: 5427132 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.6204. Min Act: -0.1700
Data Index: 209877 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.6204. Min Act: -0.1700
Data Index: 5195508 (Open Web Text)
Max Activating Token Index: 986
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.6204. Min Act: -0.1700
Data Index: 3304322 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.5892. Min Act: -0.1700
Data Index: 4100593 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.5892. Min Act: -0.1700
Data Index: 1126607 (Open Web Text)
Max Activating Token Index: 161
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.5579. Min Act: -0.1700
Data Index: 4305571 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.5267. Min Act: -0.1700
Data Index: 2000249 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.5267. Min Act: -0.1700
Data Index: 707243 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9017. Min Range: -6.9017
Max Act: 6.5267. Min Act: -0.1700
Data Index: 7032533 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #19