Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 227 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.7390. Min Act: -0.1700
Data Index: 6216261 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.7077. Min Act: -0.1700
Data Index: 6259003 (Open Web Text)
Max Activating Token Index: 15
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.7077. Min Act: -0.1700
Data Index: 7487332 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.7077. Min Act: -0.1700
Data Index: 5783505 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.7077. Min Act: -0.1700
Data Index: 5347107 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.7077. Min Act: -0.1700
Data Index: 4565200 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 7478215 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 601363 (Open Web Text)
Max Activating Token Index: 16
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 3661769 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 8360783 (Open Web Text)
Max Activating Token Index: 23
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 8251601 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 8000415 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6765. Min Act: -0.1700
Data Index: 2448931 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 4654284 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 3405200 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 4779547 (Open Web Text)
Max Activating Token Index: 28
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 5444317 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 1759588 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6445381 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7390. Min Range: -4.7390
Max Act: 4.6452. Min Act: -0.1700
Data Index: 6551882 (Open Web Text)
Max Activating Token Index: 11
Click toggle to see full text
Truncated
Full Text #19