Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3528 in Layer 4
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.3624. Min Act: -0.1700
Data Index: 2585466 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.2687. Min Act: -0.1700
Data Index: 3501648 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.2687. Min Act: -0.1700
Data Index: 1218516 (Open Web Text)
Max Activating Token Index: 118
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.2374. Min Act: -0.1700
Data Index: 2259898 (Open Web Text)
Max Activating Token Index: 244
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.2374. Min Act: -0.1700
Data Index: 2585465 (Open Web Text)
Max Activating Token Index: 210
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1437. Min Act: -0.1700
Data Index: 1218515 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1749. Min Act: -0.1700
Data Index: 3130085 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1749. Min Act: -0.1700
Data Index: 2675979 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1437. Min Act: -0.1700
Data Index: 210387 (Open Web Text)
Max Activating Token Index: 523
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1437. Min Act: -0.1700
Data Index: 7840415 (Open Web Text)
Max Activating Token Index: 88
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1437. Min Act: -0.1700
Data Index: 8070295 (Open Web Text)
Max Activating Token Index: 101
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1437. Min Act: -0.1700
Data Index: 3591258 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.1124. Min Act: -0.1700
Data Index: 8106723 (Open Web Text)
Max Activating Token Index: 351
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0812. Min Act: -0.1700
Data Index: 8140370 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0812. Min Act: -0.1700
Data Index: 2585464 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0812. Min Act: -0.1700
Data Index: 5201252 (Open Web Text)
Max Activating Token Index: 436
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0812. Min Act: -0.1700
Data Index: 1218507 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0812. Min Act: -0.1700
Data Index: 4269875 (Open Web Text)
Max Activating Token Index: 891
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0499. Min Act: -0.1700
Data Index: 210386 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.3624. Min Range: -6.3624
Max Act: 6.0499. Min Act: -0.1700
Data Index: 5711055 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #19