Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 5110 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.9633. Min Act: -0.1700
Data Index: 2016167 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.9633. Min Act: -0.1700
Data Index: 5885826 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.9633. Min Act: -0.1700
Data Index: 854161 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.9008. Min Act: -0.1700
Data Index: 3942796 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.9008. Min Act: -0.1700
Data Index: 661275 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8696. Min Act: -0.1700
Data Index: 1633135 (Open Web Text)
Max Activating Token Index: 528
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8696. Min Act: -0.1700
Data Index: 5372075 (Open Web Text)
Max Activating Token Index: 170
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 4256450 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1695
Data Index: 8617420 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8071. Min Act: -0.1700
Data Index: 5660865 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 8044398 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 584107 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 4256451 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 7719961 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 3750725 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 7676787 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 3719857 (Open Web Text)
Max Activating Token Index: 948
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8383. Min Act: -0.1700
Data Index: 3187331 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8071. Min Act: -0.1700
Data Index: 4940150 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.9633. Min Range: -4.9633
Max Act: 4.8071. Min Act: -0.1700
Data Index: 1649665 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #19