Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 1613 in Layer 17
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.9052. Min Act: -0.1700
Data Index: 1891537 (Open Web Text)
Max Activating Token Index: 972
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6237. Min Act: -0.1700
Data Index: 709631 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6393. Min Act: -0.1700
Data Index: 3404510 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6081. Min Act: -0.1700
Data Index: 3106159 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6237. Min Act: -0.1700
Data Index: 5948970 (Open Web Text)
Max Activating Token Index: 14
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6081. Min Act: -0.1700
Data Index: 7922489 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5767. Min Act: -0.1700
Data Index: 4385686 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6081. Min Act: -0.1700
Data Index: 3193161 (Open Web Text)
Max Activating Token Index: 614
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5767. Min Act: -0.1700
Data Index: 3953426 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.6081. Min Act: -0.1700
Data Index: 2030596 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5611. Min Act: -0.1700
Data Index: 4774755 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5767. Min Act: -0.1700
Data Index: 4384033 (Open Web Text)
Max Activating Token Index: 807
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5298. Min Act: -0.1700
Data Index: 4385761 (Open Web Text)
Max Activating Token Index: 19
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5298. Min Act: -0.1700
Data Index: 7396342 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.5454. Min Act: -0.1700
Data Index: 6274161 (Open Web Text)
Max Activating Token Index: 60
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.4985. Min Act: -0.1700
Data Index: 8231638 (Open Web Text)
Max Activating Token Index: 46
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.4828. Min Act: -0.1700
Data Index: 1468308 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.4828. Min Act: -0.1700
Data Index: 3852779 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.4671. Min Act: -0.1700
Data Index: 7426892 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.9052. Min Range: -3.9052
Max Act: 3.4985. Min Act: -0.1700
Data Index: 2256248 (Open Web Text)
Max Activating Token Index: 40
Click toggle to see full text
Truncated
Full Text #19