Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 21 in Layer 2
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.9452. Min Act: -0.1700
Data Index: 999986 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.8827. Min Act: -0.1700
Data Index: 3455060 (Open Web Text)
Max Activating Token Index: 109
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.8202. Min Act: -0.1700
Data Index: 3212286 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.8202. Min Act: -0.1700
Data Index: 7394408 (Open Web Text)
Max Activating Token Index: 959
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.7890. Min Act: -0.1700
Data Index: 4735607 (Open Web Text)
Max Activating Token Index: 1008
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.7577. Min Act: -0.1700
Data Index: 738170 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6952. Min Act: -0.1700
Data Index: 6831579 (Open Web Text)
Max Activating Token Index: 673
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6952. Min Act: -0.1700
Data Index: 1129943 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6640. Min Act: -0.1700
Data Index: 3212278 (Open Web Text)
Max Activating Token Index: 887
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6640. Min Act: -0.1700
Data Index: 3887896 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6640. Min Act: -0.1700
Data Index: 6290659 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6015. Min Act: -0.1700
Data Index: 4408892 (Open Web Text)
Max Activating Token Index: 392
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6640. Min Act: -0.1700
Data Index: 8560008 (Open Web Text)
Max Activating Token Index: 1021
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6327. Min Act: -0.1700
Data Index: 2771740 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6015. Min Act: -0.1700
Data Index: 3521364 (Open Web Text)
Max Activating Token Index: 123
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.6015. Min Act: -0.1700
Data Index: 4923175 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.5702. Min Act: -0.1700
Data Index: 5271851 (Open Web Text)
Max Activating Token Index: 661
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.5702. Min Act: -0.1700
Data Index: 5469625 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.5390. Min Act: -0.1700
Data Index: 2216221 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9452. Min Range: -6.9452
Max Act: 6.5390. Min Act: -0.1700
Data Index: 6567119 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #19