Model: GPT-2 Large: 36 Layers, 5120 Neurons per Layer
Dataset: Open Web Text
Neuron 3632 in Layer 9
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-large')
Text #0
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.4099. Min Act: -0.1700
Data Index: 5334619 (Open Web Text)
Max Activating Token Index: 85
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3785. Min Act: -0.1700
Data Index: 959137 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3315. Min Act: -0.1700
Data Index: 6815527 (Open Web Text)
Max Activating Token Index: 386
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3472. Min Act: -0.1700
Data Index: 2631685 (Open Web Text)
Max Activating Token Index: 208
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3158. Min Act: -0.1700
Data Index: 3500650 (Open Web Text)
Max Activating Token Index: 5
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3315. Min Act: -0.1700
Data Index: 6368396 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3001. Min Act: -0.1700
Data Index: 2511032 (Open Web Text)
Max Activating Token Index: 456
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.3158. Min Act: -0.1700
Data Index: 4060640 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2844. Min Act: -0.1700
Data Index: 7448920 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2844. Min Act: -0.1700
Data Index: 4098985 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2844. Min Act: -0.1700
Data Index: 6325749 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2687. Min Act: -0.1700
Data Index: 5739044 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2373. Min Act: -0.1700
Data Index: 2527688 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2373. Min Act: -0.1700
Data Index: 2387856 (Open Web Text)
Max Activating Token Index: 171
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2058. Min Act: -0.1700
Data Index: 7553829 (Open Web Text)
Max Activating Token Index: 12
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2058. Min Act: -0.1700
Data Index: 3878013 (Open Web Text)
Max Activating Token Index: 314
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2058. Min Act: -0.1700
Data Index: 1124561 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2215. Min Act: -0.1700
Data Index: 4226052 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.2058. Min Act: -0.1700
Data Index: 6294333 (Open Web Text)
Max Activating Token Index: 203
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.4099. Min Range: -3.4099
Max Act: 3.1901. Min Act: -0.1700
Data Index: 1632162 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #19