Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2764 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.0187. Min Range: -5.0187
Max Act: 5.0187. Min Act: -0.1700
Data Index: 5107506 (Open Web Text)
Max Activating Token Index: 388
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.8625. Min Act: -0.1700
Data Index: 1975893 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7687. Min Act: -0.1700
Data Index: 1152640 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7375. Min Act: -0.1700
Data Index: 1335538 (Open Web Text)
Max Activating Token Index: 976
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7062. Min Act: -0.1700
Data Index: 1335527 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7062. Min Act: -0.1700
Data Index: 6830216 (Open Web Text)
Max Activating Token Index: 745
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.7062. Min Act: -0.1700
Data Index: 4665 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6750. Min Act: -0.1700
Data Index: 5791867 (Open Web Text)
Max Activating Token Index: 440
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 5791869 (Open Web Text)
Max Activating Token Index: 241
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 5221265 (Open Web Text)
Max Activating Token Index: 920
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 8389938 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.6437. Min Act: -0.1700
Data Index: 5791870 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 1133391 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5499. Min Act: -0.1700
Data Index: 7671568 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5812. Min Act: -0.1700
Data Index: 3894394 (Open Web Text)
Max Activating Token Index: 271
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5499. Min Act: -0.1700
Data Index: 1335530 (Open Web Text)
Max Activating Token Index: 939
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 3290683 (Open Web Text)
Max Activating Token Index: 710
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.5187. Min Act: -0.1700
Data Index: 4569346 (Open Web Text)
Max Activating Token Index: 278
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.4874. Min Act: -0.1700
Data Index: 1919730 (Open Web Text)
Max Activating Token Index: 468
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.0187. Min Range: -5.0187
Max Act: 4.4874. Min Act: -0.1700
Data Index: 5080488 (Open Web Text)
Max Activating Token Index: 447
Click toggle to see full text
Truncated
Full Text #19