Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 787 in Layer 6
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 4.1160. Min Range: -4.1160
Max Act: 4.1160. Min Act: -0.1700
Data Index: 3416880 (Open Web Text)
Max Activating Token Index: 158
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.1160. Min Range: -4.1160
Max Act: 4.0535. Min Act: -0.1700
Data Index: 1077771 (Open Web Text)
Max Activating Token Index: 593
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.1160. Min Range: -4.1160
Max Act: 4.0848. Min Act: -0.1700
Data Index: 6703726 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.1160. Min Range: -4.1160
Max Act: 4.0848. Min Act: -0.1700
Data Index: 7432568 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.1160. Min Range: -4.1160
Max Act: 4.0223. Min Act: -0.1700
Data Index: 8255825 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.1160. Min Range: -4.1160
Max Act: 4.0223. Min Act: -0.1700
Data Index: 3615632 (Open Web Text)
Max Activating Token Index: 131
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9597. Min Act: -0.1700
Data Index: 4117334 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 1821267 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 6958624 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 1799091 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 7849063 (Open Web Text)
Max Activating Token Index: 376
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 404004 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 7432567 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 7425706 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5708696 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 6339616 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 6980967 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5691833 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 5957237 (Open Web Text)
Max Activating Token Index: 270
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.1160. Min Range: -4.1160
Max Act: 3.9285. Min Act: -0.1700
Data Index: 1151847 (Open Web Text)
Max Activating Token Index: 3
Click toggle to see full text
Truncated
Full Text #19