Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 878 in Layer 12
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.0110. Min Range: -4.0110
Max Act: 4.0110. Min Act: -0.1700
Data Index: 928659 (Open Web Text)
Max Activating Token Index: 683
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.9173. Min Act: -0.1700
Data Index: 3062573 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.7609. Min Act: -0.1700
Data Index: 1137472 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.5732. Min Act: -0.1700
Data Index: 8056333 (Open Web Text)
Max Activating Token Index: 985
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.5418. Min Act: -0.1700
Data Index: 6271477 (Open Web Text)
Max Activating Token Index: 620
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.5418. Min Act: -0.1700
Data Index: 2575219 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.5418. Min Act: -0.1700
Data Index: 8301788 (Open Web Text)
Max Activating Token Index: 803
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.5105. Min Act: -0.1700
Data Index: 5746952 (Open Web Text)
Max Activating Token Index: 125
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4949. Min Act: -0.1700
Data Index: 5001347 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4949. Min Act: -0.1700
Data Index: 2080811 (Open Web Text)
Max Activating Token Index: 59
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4635. Min Act: -0.1700
Data Index: 4472791 (Open Web Text)
Max Activating Token Index: 476
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4792. Min Act: -0.1700
Data Index: 3161363 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4635. Min Act: -0.1700
Data Index: 4840257 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4635. Min Act: -0.1700
Data Index: 8210408 (Open Web Text)
Max Activating Token Index: 533
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4322. Min Act: -0.1700
Data Index: 6438250 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4165. Min Act: -0.1700
Data Index: 3329808 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4008. Min Act: -0.1700
Data Index: 3962789 (Open Web Text)
Max Activating Token Index: 134
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4008. Min Act: -0.1700
Data Index: 8050571 (Open Web Text)
Max Activating Token Index: 195
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4008. Min Act: -0.1700
Data Index: 4845801 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.0110. Min Range: -4.0110
Max Act: 3.4165. Min Act: -0.1700
Data Index: 3599770 (Open Web Text)
Max Activating Token Index: 10
Click toggle to see full text
Truncated
Full Text #19