Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3601 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.1063. Min Range: -5.1063
Max Act: 5.1063. Min Act: -0.1700
Data Index: 2993609 (Open Web Text)
Max Activating Token Index: 582
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.9813. Min Act: -0.1700
Data Index: 5575647 (Open Web Text)
Max Activating Token Index: 260
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1063. Min Range: -5.1063
Max Act: 5.0126. Min Act: -0.1700
Data Index: 1131892 (Open Web Text)
Max Activating Token Index: 847
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1063. Min Range: -5.1063
Max Act: 5.0438. Min Act: -0.1700
Data Index: 6259887 (Open Web Text)
Max Activating Token Index: 979
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.9813. Min Act: -0.1700
Data Index: 3974026 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.9501. Min Act: -0.1700
Data Index: 4423059 (Open Web Text)
Max Activating Token Index: 872
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.9501. Min Act: -0.1700
Data Index: 3780882 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.9188. Min Act: -0.1700
Data Index: 1619528 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.9188. Min Act: -0.1700
Data Index: 2292234 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8563. Min Act: -0.1700
Data Index: 8066580 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4119034 (Open Web Text)
Max Activating Token Index: 347
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4027490 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4562623 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8251. Min Act: -0.1700
Data Index: 6468808 (Open Web Text)
Max Activating Token Index: 4
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4785175 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8563. Min Act: -0.1700
Data Index: 4020960 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8251. Min Act: -0.1700
Data Index: 7149378 (Open Web Text)
Max Activating Token Index: 776
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.7938. Min Act: -0.1700
Data Index: 4945409 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.7626. Min Act: -0.1700
Data Index: 2324841 (Open Web Text)
Max Activating Token Index: 527
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1063. Min Range: -5.1063
Max Act: 4.8251. Min Act: -0.1700
Data Index: 5303728 (Open Web Text)
Max Activating Token Index: 144
Click toggle to see full text
Truncated
Full Text #19