Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 6.1025. Min Range: -6.1025
Max Act: 6.1025. Min Act: -0.1700
Data Index: 3813461 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.1025. Min Range: -6.1025
Max Act: 6.0088. Min Act: -0.1700
Data Index: 8170079 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.8525. Min Act: -0.1700
Data Index: 6455765 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.8838. Min Act: -0.1700
Data Index: 3214744 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.8525. Min Act: -0.1700
Data Index: 3042481 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.8213. Min Act: -0.1700
Data Index: 3079468 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.8213. Min Act: -0.1700
Data Index: 6212257 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.7900. Min Act: -0.1700
Data Index: 7584542 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.7900. Min Act: -0.1700
Data Index: 3209814 (Open Web Text)
Max Activating Token Index: 408
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.7275. Min Act: -0.1700
Data Index: 4417162 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.7275. Min Act: -0.1700
Data Index: 8616466 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6963. Min Act: -0.1700
Data Index: 4588666 (Open Web Text)
Max Activating Token Index: 1018
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6650. Min Act: -0.1700
Data Index: 889766 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6650. Min Act: -0.1700
Data Index: 1121091 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6650. Min Act: -0.1700
Data Index: 1822932 (Open Web Text)
Max Activating Token Index: 334
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6650. Min Act: -0.1700
Data Index: 5651862 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6650. Min Act: -0.1700
Data Index: 4770779 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6338. Min Act: -0.1700
Data Index: 2141110 (Open Web Text)
Max Activating Token Index: 232
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6338. Min Act: -0.1700
Data Index: 2553635 (Open Web Text)
Max Activating Token Index: 758
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.1025. Min Range: -6.1025
Max Act: 5.6025. Min Act: -0.1700
Data Index: 3748869 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19