Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 2802 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 4.2063. Min Range: -4.2063
Max Act: 4.2063. Min Act: -0.1700
Data Index: 4469638 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2063. Min Range: -4.2063
Max Act: 4.0813. Min Act: -0.1700
Data Index: 734609 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2063. Min Range: -4.2063
Max Act: 4.0188. Min Act: -0.1700
Data Index: 5676827 (Open Web Text)
Max Activating Token Index: 196
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2063. Min Range: -4.2063
Max Act: 4.0500. Min Act: -0.1700
Data Index: 8503102 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2063. Min Range: -4.2063
Max Act: 4.0188. Min Act: -0.1700
Data Index: 6269582 (Open Web Text)
Max Activating Token Index: 242
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2063. Min Range: -4.2063
Max Act: 4.0188. Min Act: -0.1700
Data Index: 8487545 (Open Web Text)
Max Activating Token Index: 706
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.9875. Min Act: -0.1700
Data Index: 1601156 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.9562. Min Act: -0.1700
Data Index: 5963475 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.9250. Min Act: -0.1700
Data Index: 11301 (Open Web Text)
Max Activating Token Index: 889
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.9250. Min Act: -0.1700
Data Index: 11300 (Open Web Text)
Max Activating Token Index: 24
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.9250. Min Act: -0.1700
Data Index: 1146935 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8781. Min Act: -0.1700
Data Index: 7327633 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8937. Min Act: -0.1700
Data Index: 651241 (Open Web Text)
Max Activating Token Index: 988
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8937. Min Act: -0.1700
Data Index: 2463320 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8937. Min Act: -0.1700
Data Index: 2962272 (Open Web Text)
Max Activating Token Index: 293
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8937. Min Act: -0.1700
Data Index: 4170839 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8781. Min Act: -0.1700
Data Index: 2068924 (Open Web Text)
Max Activating Token Index: 793
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8781. Min Act: -0.1700
Data Index: 5688812 (Open Web Text)
Max Activating Token Index: 72
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8937. Min Act: -0.1700
Data Index: 7405929 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2063. Min Range: -4.2063
Max Act: 3.8625. Min Act: -0.1700
Data Index: 8273930 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #19