Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2760 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.7627. Min Act: -0.1700
Data Index: 7691269 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.7627. Min Act: -0.1700
Data Index: 5379353 (Open Web Text)
Max Activating Token Index: 691
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.7314. Min Act: -0.1700
Data Index: 4807785 (Open Web Text)
Max Activating Token Index: 794
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.7314. Min Act: -0.1700
Data Index: 944975 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.5439. Min Act: -0.1700
Data Index: 7815925 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.5127. Min Act: -0.1700
Data Index: 5913180 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4814. Min Act: -0.1700
Data Index: 6070672 (Open Web Text)
Max Activating Token Index: 98
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4502. Min Act: -0.1700
Data Index: 6178640 (Open Web Text)
Max Activating Token Index: 1007
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4502. Min Act: -0.1700
Data Index: 8728781 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4502. Min Act: -0.1700
Data Index: 5141899 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4502. Min Act: -0.1700
Data Index: 756113 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4189. Min Act: -0.1700
Data Index: 657569 (Open Web Text)
Max Activating Token Index: 164
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.4189. Min Act: -0.1700
Data Index: 7759950 (Open Web Text)
Max Activating Token Index: 535
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3877. Min Act: -0.1700
Data Index: 5489061 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3877. Min Act: -0.1700
Data Index: 6704279 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3564. Min Act: -0.1700
Data Index: 4521818 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3877. Min Act: -0.1700
Data Index: 6109688 (Open Web Text)
Max Activating Token Index: 69
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3564. Min Act: -0.1700
Data Index: 4629572 (Open Web Text)
Max Activating Token Index: 987
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3564. Min Act: -0.1700
Data Index: 5934254 (Open Web Text)
Max Activating Token Index: 54
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7627. Min Range: -4.7627
Max Act: 4.3564. Min Act: -0.1700
Data Index: 3879027 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #19