Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 50 in Layer 5
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.1188. Min Range: -5.1188
Max Act: 5.1188. Min Act: -0.1700
Data Index: 2123501 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.1188. Min Range: -5.1188
Max Act: 5.0251. Min Act: -0.1700
Data Index: 4941408 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.9626. Min Act: -0.1700
Data Index: 5406217 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.9001. Min Act: -0.1700
Data Index: 7732008 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.8688. Min Act: -0.1700
Data Index: 1642829 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.8688. Min Act: -0.1700
Data Index: 263481 (Open Web Text)
Max Activating Token Index: 787
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.8376. Min Act: -0.1700
Data Index: 159322 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.8688. Min Act: -0.1700
Data Index: 3618875 (Open Web Text)
Max Activating Token Index: 70
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.8063. Min Act: -0.1700
Data Index: 6028832 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7438. Min Act: -0.1700
Data Index: 724205 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7438. Min Act: -0.1700
Data Index: 3739316 (Open Web Text)
Max Activating Token Index: 404
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7126. Min Act: -0.1700
Data Index: 3068157 (Open Web Text)
Max Activating Token Index: 330
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7126. Min Act: -0.1700
Data Index: 1951741 (Open Web Text)
Max Activating Token Index: 108
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7126. Min Act: -0.1700
Data Index: 5597991 (Open Web Text)
Max Activating Token Index: 501
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7126. Min Act: -0.1700
Data Index: 8786262 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.7126. Min Act: -0.1700
Data Index: 8743490 (Open Web Text)
Max Activating Token Index: 943
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.6813. Min Act: -0.1700
Data Index: 2736622 (Open Web Text)
Max Activating Token Index: 754
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.6813. Min Act: -0.1700
Data Index: 4596848 (Open Web Text)
Max Activating Token Index: 992
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.6813. Min Act: -0.1700
Data Index: 7646725 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.1188. Min Range: -5.1188
Max Act: 4.6813. Min Act: -0.1700
Data Index: 8076644 (Open Web Text)
Max Activating Token Index: 308
Click toggle to see full text
Truncated
Full Text #19