Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 3865 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.7812. Min Act: -0.1700
Data Index: 422805 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.7499. Min Act: -0.1700
Data Index: 6754591 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.7187. Min Act: -0.1700
Data Index: 6411494 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6874. Min Act: -0.1700
Data Index: 5920165 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.7187. Min Act: -0.1700
Data Index: 7878425 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6874. Min Act: -0.1700
Data Index: 1114177 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6562. Min Act: -0.1700
Data Index: 7592321 (Open Web Text)
Max Activating Token Index: 562
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6562. Min Act: -0.1700
Data Index: 5887950 (Open Web Text)
Max Activating Token Index: 511
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 4529445 (Open Web Text)
Max Activating Token Index: 33
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6562. Min Act: -0.1700
Data Index: 4198179 (Open Web Text)
Max Activating Token Index: 184
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6562. Min Act: -0.1700
Data Index: 3448185 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6562. Min Act: -0.1700
Data Index: 3142656 (Open Web Text)
Max Activating Token Index: 245
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 8043745 (Open Web Text)
Max Activating Token Index: 926
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 20359 (Open Web Text)
Max Activating Token Index: 193
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 372812 (Open Web Text)
Max Activating Token Index: 177
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 6229735 (Open Web Text)
Max Activating Token Index: 696
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6874. Min Act: -0.1700
Data Index: 5128056 (Open Web Text)
Max Activating Token Index: 929
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 5163234 (Open Web Text)
Max Activating Token Index: 563
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 8560746 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.7812. Min Range: -5.7812
Max Act: 5.6249. Min Act: -0.1700
Data Index: 4967811 (Open Web Text)
Max Activating Token Index: 443
Click toggle to see full text
Truncated
Full Text #19