Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4 in Layer 47
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.2006. Min Range: -9.2006
Max Act: 9.2006. Min Act: -0.1700
Data Index: 6035531 (Open Web Text)
Max Activating Token Index: 755
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.2006. Min Range: -9.2006
Max Act: 9.2006. Min Act: -0.1700
Data Index: 7604481 (Open Web Text)
Max Activating Token Index: 305
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.2006. Min Range: -9.2006
Max Act: 9.0756. Min Act: -0.1700
Data Index: 2043817 (Open Web Text)
Max Activating Token Index: 903
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.8256. Min Act: -0.1700
Data Index: 6035522 (Open Web Text)
Max Activating Token Index: 137
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.8881. Min Act: -0.1700
Data Index: 3348472 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.8256. Min Act: -0.1700
Data Index: 766527 (Open Web Text)
Max Activating Token Index: 824
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.7006. Min Act: -0.1700
Data Index: 765054 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.5756. Min Act: -0.1700
Data Index: 1381824 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.5756. Min Act: -0.1700
Data Index: 3630725 (Open Web Text)
Max Activating Token Index: 564
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.5131. Min Act: -0.1700
Data Index: 114725 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.4506. Min Act: -0.1700
Data Index: 745603 (Open Web Text)
Max Activating Token Index: 945
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.4506. Min Act: -0.1700
Data Index: 4804525 (Open Web Text)
Max Activating Token Index: 795
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.4506. Min Act: -0.1700
Data Index: 1619633 (Open Web Text)
Max Activating Token Index: 605
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 2501173 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 3303838 (Open Web Text)
Max Activating Token Index: 662
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 5832949 (Open Web Text)
Max Activating Token Index: 459
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 2878761 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 6652779 (Open Web Text)
Max Activating Token Index: 548
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 7122355 (Open Web Text)
Max Activating Token Index: 645
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.2006. Min Range: -9.2006
Max Act: 8.3881. Min Act: -0.1700
Data Index: 5753256 (Open Web Text)
Max Activating Token Index: 628
Click toggle to see full text
Truncated
Full Text #19