Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3631 in Layer 22
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.5905. Min Act: -0.1700
Data Index: 1666431 (Open Web Text)
Max Activating Token Index: 261
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.5905. Min Act: -0.1700
Data Index: 2088886 (Open Web Text)
Max Activating Token Index: 369
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.4968. Min Act: -0.1700
Data Index: 2155333 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.4030. Min Act: -0.1700
Data Index: 795260 (Open Web Text)
Max Activating Token Index: 877
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.4030. Min Act: -0.1700
Data Index: 1005556 (Open Web Text)
Max Activating Token Index: 577
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.3718. Min Act: -0.1700
Data Index: 7680966 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.3718. Min Act: -0.1700
Data Index: 1462313 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.3093. Min Act: -0.1700
Data Index: 6792754 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.3093. Min Act: -0.1700
Data Index: 8693583 (Open Web Text)
Max Activating Token Index: 25
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.3093. Min Act: -0.1700
Data Index: 8793889 (Open Web Text)
Max Activating Token Index: 967
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.3093. Min Act: -0.1700
Data Index: 4036350 (Open Web Text)
Max Activating Token Index: 130
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2468. Min Act: -0.1700
Data Index: 7739417 (Open Web Text)
Max Activating Token Index: 557
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2780. Min Act: -0.1700
Data Index: 6140379 (Open Web Text)
Max Activating Token Index: 102
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2468. Min Act: -0.1700
Data Index: 5207756 (Open Web Text)
Max Activating Token Index: 32
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2468. Min Act: -0.1700
Data Index: 677830 (Open Web Text)
Max Activating Token Index: 396
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2468. Min Act: -0.1700
Data Index: 8383387 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2468. Min Act: -0.1700
Data Index: 6086719 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.2468. Min Act: -0.1700
Data Index: 8494525 (Open Web Text)
Max Activating Token Index: 200
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.1843. Min Act: -0.1700
Data Index: 1512434 (Open Web Text)
Max Activating Token Index: 120
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5905. Min Range: -6.5905
Max Act: 6.1843. Min Act: -0.1700
Data Index: 7587658 (Open Web Text)
Max Activating Token Index: 49
Click toggle to see full text
Truncated
Full Text #19