Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 113 in Layer 31
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.7370. Min Act: -0.1700
Data Index: 627902 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.6745. Min Act: -0.1700
Data Index: 3825316 (Open Web Text)
Max Activating Token Index: 457
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.5495. Min Act: -0.1700
Data Index: 451655 (Open Web Text)
Max Activating Token Index: 806
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.4558. Min Act: -0.1700
Data Index: 2360338 (Open Web Text)
Max Activating Token Index: 651
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.3933. Min Act: -0.1700
Data Index: 8390008 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.3308. Min Act: -0.1700
Data Index: 982590 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.2995. Min Act: -0.1700
Data Index: 933731 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.2683. Min Act: -0.1700
Data Index: 3133954 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.2683. Min Act: -0.1700
Data Index: 7379810 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.2370. Min Act: -0.1700
Data Index: 2718896 (Open Web Text)
Max Activating Token Index: 174
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.2370. Min Act: -0.1700
Data Index: 67276 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.2058. Min Act: -0.1700
Data Index: 5444396 (Open Web Text)
Max Activating Token Index: 596
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1745. Min Act: -0.1700
Data Index: 4565815 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1745. Min Act: -0.1700
Data Index: 5488461 (Open Web Text)
Max Activating Token Index: 335
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1745. Min Act: -0.1700
Data Index: 5208079 (Open Web Text)
Max Activating Token Index: 236
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1433. Min Act: -0.1700
Data Index: 8401143 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1433. Min Act: -0.1700
Data Index: 4659173 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1433. Min Act: -0.1700
Data Index: 3896848 (Open Web Text)
Max Activating Token Index: 684
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1120. Min Act: -0.1700
Data Index: 1858586 (Open Web Text)
Max Activating Token Index: 820
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7370. Min Range: -7.7370
Max Act: 7.1120. Min Act: -0.1700
Data Index: 7806292 (Open Web Text)
Max Activating Token Index: 469
Click toggle to see full text
Truncated
Full Text #19