Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 6168 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1751. Min Range: -7.1751
Max Act: 7.1751. Min Act: -0.1700
Data Index: 7191050 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.5813. Min Act: -0.1700
Data Index: 3538040 (Open Web Text)
Max Activating Token Index: 568
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.4563. Min Act: -0.1700
Data Index: 4649683 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.3626. Min Act: -0.1700
Data Index: 5541474 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.3626. Min Act: -0.1700
Data Index: 2289833 (Open Web Text)
Max Activating Token Index: 318
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.3626. Min Act: -0.1700
Data Index: 7930539 (Open Web Text)
Max Activating Token Index: 218
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.2376. Min Act: -0.1700
Data Index: 2435831 (Open Web Text)
Max Activating Token Index: 479
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.2376. Min Act: -0.1700
Data Index: 7798708 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.2063. Min Act: -0.1700
Data Index: 6600926 (Open Web Text)
Max Activating Token Index: 894
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.2063. Min Act: -0.1700
Data Index: 7309743 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.2063. Min Act: -0.1700
Data Index: 7566395 (Open Web Text)
Max Activating Token Index: 135
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1751. Min Act: -0.1700
Data Index: 532405 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1438. Min Act: -0.1700
Data Index: 7457831 (Open Web Text)
Max Activating Token Index: 1001
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1438. Min Act: -0.1700
Data Index: 2999432 (Open Web Text)
Max Activating Token Index: 433
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1438. Min Act: -0.1700
Data Index: 884327 (Open Web Text)
Max Activating Token Index: 607
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1438. Min Act: -0.1700
Data Index: 5313419 (Open Web Text)
Max Activating Token Index: 381
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1438. Min Act: -0.1700
Data Index: 5002441 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1126. Min Act: -0.1700
Data Index: 202217 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1126. Min Act: -0.1700
Data Index: 2888673 (Open Web Text)
Max Activating Token Index: 194
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1751. Min Range: -7.1751
Max Act: 6.1126. Min Act: -0.1700
Data Index: 6070698 (Open Web Text)
Max Activating Token Index: 235
Click toggle to see full text
Truncated
Full Text #19