Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2732 in Layer 15
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.2597. Min Range: -4.2597
Max Act: 4.2597. Min Act: -0.1700
Data Index: 333856 (Open Web Text)
Max Activating Token Index: 998
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2597. Min Range: -4.2597
Max Act: 4.0722. Min Act: -0.1700
Data Index: 601260 (Open Web Text)
Max Activating Token Index: 659
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2597. Min Range: -4.2597
Max Act: 4.0097. Min Act: -0.1700
Data Index: 4565351 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2597. Min Range: -4.2597
Max Act: 4.0097. Min Act: -0.1700
Data Index: 6156611 (Open Web Text)
Max Activating Token Index: 536
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.9784. Min Act: -0.1700
Data Index: 1506702 (Open Web Text)
Max Activating Token Index: 309
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.9315. Min Act: -0.1700
Data Index: 4517040 (Open Web Text)
Max Activating Token Index: 380
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.9159. Min Act: -0.1700
Data Index: 7670070 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8377. Min Act: -0.1700
Data Index: 4601839 (Open Web Text)
Max Activating Token Index: 580
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8377. Min Act: -0.1700
Data Index: 7532736 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8221. Min Act: -0.1700
Data Index: 3077487 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8221. Min Act: -0.1700
Data Index: 4787653 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8065. Min Act: -0.1700
Data Index: 2725131 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.7908. Min Act: -0.1700
Data Index: 6345434 (Open Web Text)
Max Activating Token Index: 627
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8065. Min Act: -0.1700
Data Index: 4035014 (Open Web Text)
Max Activating Token Index: 738
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.7752. Min Act: -0.1700
Data Index: 5551069 (Open Web Text)
Max Activating Token Index: 73
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8065. Min Act: -0.1700
Data Index: 3876959 (Open Web Text)
Max Activating Token Index: 543
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.8065. Min Act: -0.1700
Data Index: 8278751 (Open Web Text)
Max Activating Token Index: 139
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.7908. Min Act: -0.1700
Data Index: 6305438 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.7752. Min Act: -0.1700
Data Index: 5068494 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2597. Min Range: -4.2597
Max Act: 3.7908. Min Act: -0.1700
Data Index: 1688678 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #19