Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4553 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.6824. Min Act: -0.1700
Data Index: 2020205 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.6512. Min Act: -0.1700
Data Index: 8520227 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.5262. Min Act: -0.1700
Data Index: 4310263 (Open Web Text)
Max Activating Token Index: 92
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.4949. Min Act: -0.1700
Data Index: 5893067 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.4637. Min Act: -0.1700
Data Index: 6516097 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.4637. Min Act: -0.1700
Data Index: 8653552 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.4012. Min Act: -0.1700
Data Index: 917763 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.4012. Min Act: -0.1700
Data Index: 8653554 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3699. Min Act: -0.1700
Data Index: 6951146 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3699. Min Act: -0.1700
Data Index: 4631267 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 7007731 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 4113434 (Open Web Text)
Max Activating Token Index: 91
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 3681793 (Open Web Text)
Max Activating Token Index: 186
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 6849994 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3699. Min Act: -0.1700
Data Index: 1503905 (Open Web Text)
Max Activating Token Index: 95
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 6997803 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 6970633 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3387. Min Act: -0.1700
Data Index: 317153 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3074. Min Act: -0.1700
Data Index: 1430561 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.6824. Min Range: -4.6824
Max Act: 4.3074. Min Act: -0.1700
Data Index: 2477888 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #19