Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5115 in Layer 18
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.5063. Min Act: -0.1700
Data Index: 991945 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.3813. Min Act: -0.1700
Data Index: 4434436 (Open Web Text)
Max Activating Token Index: 446
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.2251. Min Act: -0.1700
Data Index: 71942 (Open Web Text)
Max Activating Token Index: 633
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.1626. Min Act: -0.1700
Data Index: 6623661 (Open Web Text)
Max Activating Token Index: 844
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.1313. Min Act: -0.1700
Data Index: 4795619 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.0688. Min Act: -0.1700
Data Index: 1342491 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.0688. Min Act: -0.1700
Data Index: 3039863 (Open Web Text)
Max Activating Token Index: 740
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.0376. Min Act: -0.1700
Data Index: 1660425 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.0376. Min Act: -0.1700
Data Index: 5095097 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.5063. Min Range: -5.5063
Max Act: 5.0063. Min Act: -0.1700
Data Index: 1266699 (Open Web Text)
Max Activating Token Index: 364
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 6231481 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9751. Min Act: -0.1700
Data Index: 4221354 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9751. Min Act: -0.1700
Data Index: 4171040 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9751. Min Act: -0.1700
Data Index: 5560368 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 4229268 (Open Web Text)
Max Activating Token Index: 401
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 1612208 (Open Web Text)
Max Activating Token Index: 51
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 7226724 (Open Web Text)
Max Activating Token Index: 480
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 1044603 (Open Web Text)
Max Activating Token Index: 321
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 7004595 (Open Web Text)
Max Activating Token Index: 250
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.5063. Min Range: -5.5063
Max Act: 4.9438. Min Act: -0.1700
Data Index: 7549684 (Open Web Text)
Max Activating Token Index: 546
Click toggle to see full text
Truncated
Full Text #19