Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1719 in Layer 33
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 7.0593. Min Range: -7.0593
Max Act: 7.0593. Min Act: -0.1700
Data Index: 5716536 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.9030. Min Act: -0.1700
Data Index: 8091141 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8718. Min Act: -0.1700
Data Index: 803954 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8718. Min Act: -0.1700
Data Index: 4615063 (Open Web Text)
Max Activating Token Index: 732
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 6178452 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 495354 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8718. Min Act: -0.1700
Data Index: 6218514 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 7587618 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 5149729 (Open Web Text)
Max Activating Token Index: 908
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 6841692 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 7112106 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8093. Min Act: -0.1700
Data Index: 495353 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.7780. Min Act: -0.1700
Data Index: 6841693 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8405. Min Act: -0.1700
Data Index: 7112105 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8093. Min Act: -0.1700
Data Index: 384794 (Open Web Text)
Max Activating Token Index: 693
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.7780. Min Act: -0.1700
Data Index: 5149730 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8093. Min Act: -0.1700
Data Index: 4779574 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.7780. Min Act: -0.1700
Data Index: 8091142 (Open Web Text)
Max Activating Token Index: 915
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.8093. Min Act: -0.1700
Data Index: 146098 (Open Web Text)
Max Activating Token Index: 140
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.0593. Min Range: -7.0593
Max Act: 6.7780. Min Act: -0.1700
Data Index: 3312077 (Open Web Text)
Max Activating Token Index: 425
Click toggle to see full text
Truncated
Full Text #19