Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1347 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.3879. Min Act: -0.1700
Data Index: 3435858 (Open Web Text)
Max Activating Token Index: 649
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.3254. Min Act: -0.1700
Data Index: 1017652 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.2629. Min Act: -0.1700
Data Index: 6031802 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.2629. Min Act: -0.1700
Data Index: 4794077 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.2629. Min Act: -0.1700
Data Index: 4310184 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.2004. Min Act: -0.1700
Data Index: 3897095 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.1379. Min Act: -0.1700
Data Index: 4420146 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.1379. Min Act: -0.1700
Data Index: 1374070 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.1379. Min Act: -0.1700
Data Index: 291632 (Open Web Text)
Max Activating Token Index: 573
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.1379. Min Act: -0.1700
Data Index: 8063131 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 4394858 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 1630538 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 8658162 (Open Web Text)
Max Activating Token Index: 400
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 3684659 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 5272007 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 647239 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 1262583 (Open Web Text)
Max Activating Token Index: 1003
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0754. Min Act: -0.1700
Data Index: 4416261 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.3879. Min Range: -8.3879
Max Act: 8.0129. Min Act: -0.1700
Data Index: 3806561 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.3879. Min Range: -8.3879
Max Act: 7.9504. Min Act: -0.1700
Data Index: 5127746 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #19