Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2279 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.4842. Min Act: -0.1700
Data Index: 227044 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.4058. Min Act: -0.1700
Data Index: 5883603 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.4215. Min Act: -0.1700
Data Index: 8431905 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.3117. Min Act: -0.1700
Data Index: 7330596 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.3274. Min Act: -0.1700
Data Index: 5095736 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.2803. Min Act: -0.1700
Data Index: 1764437 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.2803. Min Act: -0.1700
Data Index: 6890029 (Open Web Text)
Max Activating Token Index: 525
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.2646. Min Act: -0.1700
Data Index: 2285308 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.2018. Min Act: -0.1700
Data Index: 2477698 (Open Web Text)
Max Activating Token Index: 781
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.2175. Min Act: -0.1700
Data Index: 8245560 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1860. Min Act: -0.1700
Data Index: 7040869 (Open Web Text)
Max Activating Token Index: 65
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1703. Min Act: -0.1700
Data Index: 1654436 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1860. Min Act: -0.1700
Data Index: 5456526 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1703. Min Act: -0.1700
Data Index: 153960 (Open Web Text)
Max Activating Token Index: 413
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1546. Min Act: -0.1700
Data Index: 5027097 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1546. Min Act: -0.1700
Data Index: 8546618 (Open Web Text)
Max Activating Token Index: 1012
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1546. Min Act: -0.1700
Data Index: 8355851 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1546. Min Act: -0.1700
Data Index: 2093486 (Open Web Text)
Max Activating Token Index: 876
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1073. Min Act: -0.1700
Data Index: 6152855 (Open Web Text)
Max Activating Token Index: 76
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4842. Min Range: -3.4842
Max Act: 3.1073. Min Act: -0.1700
Data Index: 2468068 (Open Web Text)
Max Activating Token Index: 856
Click toggle to see full text
Truncated
Full Text #19