Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3304 in Layer 0
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.1158. Min Act: -0.1700
Data Index: 8377581 (Open Web Text)
Max Activating Token Index: 17
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.1158. Min Act: -0.1700
Data Index: 2609268 (Open Web Text)
Max Activating Token Index: 21
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0843. Min Act: -0.1700
Data Index: 6411796 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0528. Min Act: -0.1700
Data Index: 202802 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0528. Min Act: -0.1700
Data Index: 4359730 (Open Web Text)
Max Activating Token Index: 7
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0212. Min Act: -0.1700
Data Index: 2418425 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0212. Min Act: -0.1700
Data Index: 6654005 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0212. Min Act: -0.1700
Data Index: 2397144 (Open Web Text)
Max Activating Token Index: 1023
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 3265769 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 5266561 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 8277207 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 5258459 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 8536661 (Open Web Text)
Max Activating Token Index: 27
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 802265 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.1158. Min Range: -3.1158
Max Act: 3.0054. Min Act: -0.1700
Data Index: 3823861 (Open Web Text)
Max Activating Token Index: 67
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.1158. Min Range: -3.1158
Max Act: 2.9896. Min Act: -0.1700
Data Index: 1648784 (Open Web Text)
Max Activating Token Index: 13
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.1158. Min Range: -3.1158
Max Act: 2.9896. Min Act: -0.1700
Data Index: 4432369 (Open Web Text)
Max Activating Token Index: 6
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.1158. Min Range: -3.1158
Max Act: 2.9896. Min Act: -0.1700
Data Index: 2925332 (Open Web Text)
Max Activating Token Index: 34
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.1158. Min Range: -3.1158
Max Act: 2.9896. Min Act: -0.1700
Data Index: 5308477 (Open Web Text)
Max Activating Token Index: 8
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.1158. Min Range: -3.1158
Max Act: 2.9896. Min Act: -0.1700
Data Index: 8325099 (Open Web Text)
Max Activating Token Index: 18
Click toggle to see full text
Truncated
Full Text #19