Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3935 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.4616. Min Act: -0.1700
Data Index: 2985015 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.4303. Min Act: -0.1700
Data Index: 4691123 (Open Web Text)
Max Activating Token Index: 980
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3989. Min Act: -0.1700
Data Index: 7076469 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3989. Min Act: -0.1700
Data Index: 7846417 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3832. Min Act: -0.1700
Data Index: 4389110 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3519. Min Act: -0.1700
Data Index: 1837838 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3676. Min Act: -0.1700
Data Index: 2861318 (Open Web Text)
Max Activating Token Index: 874
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3676. Min Act: -0.1700
Data Index: 3876408 (Open Web Text)
Max Activating Token Index: 921
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3676. Min Act: -0.1700
Data Index: 8253393 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3832. Min Act: -0.1700
Data Index: 4080839 (Open Web Text)
Max Activating Token Index: 879
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3519. Min Act: -0.1700
Data Index: 6038673 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3362. Min Act: -0.1700
Data Index: 2414651 (Open Web Text)
Max Activating Token Index: 646
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3519. Min Act: -0.1700
Data Index: 228764 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3676. Min Act: -0.1700
Data Index: 99152 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3519. Min Act: -0.1700
Data Index: 7198930 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3676. Min Act: -0.1700
Data Index: 5946789 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3519. Min Act: -0.1700
Data Index: 7110533 (Open Web Text)
Max Activating Token Index: 567
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3362. Min Act: -0.1700
Data Index: 4287598 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3205. Min Act: -0.1700
Data Index: 6927809 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4616. Min Range: -3.4616
Max Act: 3.3048. Min Act: -0.1700
Data Index: 3536427 (Open Web Text)
Max Activating Token Index: 700
Click toggle to see full text
Truncated
Full Text #19