Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3548 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.8294. Min Act: -0.1700
Data Index: 6479566 (Open Web Text)
Max Activating Token Index: 62
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7982. Min Act: -0.1700
Data Index: 4663226 (Open Web Text)
Max Activating Token Index: 360
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.8294. Min Act: -0.1700
Data Index: 5984505 (Open Web Text)
Max Activating Token Index: 642
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7982. Min Act: -0.1700
Data Index: 6643856 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7357. Min Act: -0.1700
Data Index: 1474531 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7357. Min Act: -0.1700
Data Index: 2454765 (Open Web Text)
Max Activating Token Index: 682
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7357. Min Act: -0.1700
Data Index: 7059216 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7357. Min Act: -0.1700
Data Index: 8716581 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.7357. Min Act: -0.1700
Data Index: 7334005 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.6732. Min Act: -0.1700
Data Index: 6947474 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.6732. Min Act: -0.1700
Data Index: 7267092 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.6732. Min Act: -0.1700
Data Index: 8079544 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.6732. Min Act: -0.1700
Data Index: 6357879 (Open Web Text)
Max Activating Token Index: 619
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.6419. Min Act: -0.1700
Data Index: 7766340 (Open Web Text)
Max Activating Token Index: 291
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.6419. Min Act: -0.1700
Data Index: 1383660 (Open Web Text)
Max Activating Token Index: 950
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5794. Min Act: -0.1700
Data Index: 2246601 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5794. Min Act: -0.1700
Data Index: 5274814 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5794. Min Act: -0.1700
Data Index: 4210516 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5794. Min Act: -0.1700
Data Index: 2386069 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.8294. Min Range: -5.8294
Max Act: 5.5482. Min Act: -0.1700
Data Index: 6770481 (Open Web Text)
Max Activating Token Index: 829
Click toggle to see full text
Truncated
Full Text #19