Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2472 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 6.1298. Min Range: -6.1298
Max Act: 6.0985. Min Act: -0.1700
Data Index: 1416571 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1298. Min Range: -6.1298
Max Act: 6.1298. Min Act: -0.1700
Data Index: 514155 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1298. Min Range: -6.1298
Max Act: 6.0048. Min Act: -0.1700
Data Index: 2659521 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1298. Min Range: -6.1298
Max Act: 6.0048. Min Act: -0.1700
Data Index: 166814 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.9735. Min Act: -0.1700
Data Index: 6031679 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.9735. Min Act: -0.1700
Data Index: 5999203 (Open Web Text)
Max Activating Token Index: 995
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.9110. Min Act: -0.1700
Data Index: 3941921 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.9423. Min Act: -0.1700
Data Index: 839129 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.8485. Min Act: -0.1700
Data Index: 6031678 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.8485. Min Act: -0.1700
Data Index: 7063660 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.7235. Min Act: -0.1700
Data Index: 2187528 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.7548. Min Act: -0.1700
Data Index: 829949 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.7235. Min Act: -0.1700
Data Index: 578166 (Open Web Text)
Max Activating Token Index: 216
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.6923. Min Act: -0.1700
Data Index: 4406038 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.7235. Min Act: -0.1700
Data Index: 5806020 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.6923. Min Act: -0.1700
Data Index: 4089244 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.7235. Min Act: -0.1700
Data Index: 1513142 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.6610. Min Act: -0.1700
Data Index: 3466861 (Open Web Text)
Max Activating Token Index: 385
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.6923. Min Act: -0.1700
Data Index: 2857806 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1298. Min Range: -6.1298
Max Act: 5.6298. Min Act: -0.1700
Data Index: 1214452 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #19