Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2661 in Layer 40
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.0508. Min Range: -9.0508
Max Act: 9.0508. Min Act: -0.1700
Data Index: 7800939 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.9883. Min Act: -0.1700
Data Index: 1034613 (Open Web Text)
Max Activating Token Index: 298
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.9258. Min Act: -0.1700
Data Index: 7315712 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.8008. Min Act: -0.1700
Data Index: 6609635 (Open Web Text)
Max Activating Token Index: 375
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.7383. Min Act: -0.1700
Data Index: 5063267 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.6758. Min Act: -0.1700
Data Index: 1573067 (Open Web Text)
Max Activating Token Index: 262
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.6758. Min Act: -0.1700
Data Index: 8620749 (Open Web Text)
Max Activating Token Index: 602
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.6133. Min Act: -0.1700
Data Index: 8147657 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.6133. Min Act: -0.1700
Data Index: 1563625 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.6133. Min Act: -0.1700
Data Index: 5044536 (Open Web Text)
Max Activating Token Index: 650
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.5508. Min Act: -0.1700
Data Index: 7173748 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.5508. Min Act: -0.1700
Data Index: 7723103 (Open Web Text)
Max Activating Token Index: 1013
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.4883. Min Act: -0.1700
Data Index: 1658716 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.4258. Min Act: -0.1700
Data Index: 1037675 (Open Web Text)
Max Activating Token Index: 464
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.4258. Min Act: -0.1700
Data Index: 5934004 (Open Web Text)
Max Activating Token Index: 690
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.4883. Min Act: -0.1700
Data Index: 203713 (Open Web Text)
Max Activating Token Index: 938
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.3633. Min Act: -0.1700
Data Index: 3342006 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.3633. Min Act: -0.1700
Data Index: 5710284 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.3633. Min Act: -0.1700
Data Index: 5004485 (Open Web Text)
Max Activating Token Index: 165
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.0508. Min Range: -9.0508
Max Act: 8.3633. Min Act: -0.1700
Data Index: 1518301 (Open Web Text)
Max Activating Token Index: 116
Click toggle to see full text
Truncated
Full Text #19