Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3338 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0187. Min Range: -9.0187
Max Act: 9.0187. Min Act: -0.1700
Data Index: 22801 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.9562. Min Act: -0.1700
Data Index: 7019740 (Open Web Text)
Max Activating Token Index: 229
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.8937. Min Act: -0.1700
Data Index: 6117226 (Open Web Text)
Max Activating Token Index: 513
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.8312. Min Act: -0.1700
Data Index: 8116666 (Open Web Text)
Max Activating Token Index: 215
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.7062. Min Act: -0.1700
Data Index: 4331644 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.6437. Min Act: -0.1700
Data Index: 8194637 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.6437. Min Act: -0.1700
Data Index: 295739 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.5812. Min Act: -0.1700
Data Index: 1138752 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.6437. Min Act: -0.1700
Data Index: 4793121 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.5812. Min Act: -0.1700
Data Index: 6404086 (Open Web Text)
Max Activating Token Index: 486
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.5187. Min Act: -0.1700
Data Index: 1717248 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.5187. Min Act: -0.1700
Data Index: 6765662 (Open Web Text)
Max Activating Token Index: 744
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.5187. Min Act: -0.1700
Data Index: 4195000 (Open Web Text)
Max Activating Token Index: 504
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.5187. Min Act: -0.1700
Data Index: 7733629 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.4562. Min Act: -0.1699
Data Index: 1228194 (Open Web Text)
Max Activating Token Index: 42
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 2187677 (Open Web Text)
Max Activating Token Index: 426
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 5805078 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 6765663 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.3937. Min Act: -0.1700
Data Index: 3782125 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0187. Min Range: -9.0187
Max Act: 8.4562. Min Act: -0.1700
Data Index: 6318247 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #19