Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3161 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.3015. Min Range: -7.3015
Max Act: 7.3015. Min Act: -0.1700
Data Index: 2441688 (Open Web Text)
Max Activating Token Index: 603
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.3015. Min Range: -7.3015
Max Act: 7.3015. Min Act: -0.1700
Data Index: 6234121 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.3015. Min Range: -7.3015
Max Act: 7.2702. Min Act: -0.1700
Data Index: 7058595 (Open Web Text)
Max Activating Token Index: 997
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.3015. Min Range: -7.3015
Max Act: 7.2390. Min Act: -0.1700
Data Index: 3750761 (Open Web Text)
Max Activating Token Index: 416
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.3015. Min Range: -7.3015
Max Act: 7.0515. Min Act: -0.1700
Data Index: 1345614 (Open Web Text)
Max Activating Token Index: 882
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.9577. Min Act: -0.1700
Data Index: 333686 (Open Web Text)
Max Activating Token Index: 269
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8952. Min Act: -0.1700
Data Index: 6448655 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8952. Min Act: -0.1700
Data Index: 6291479 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8640. Min Act: -0.1700
Data Index: 5471104 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8015. Min Act: -0.1700
Data Index: 5413877 (Open Web Text)
Max Activating Token Index: 669
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8015. Min Act: -0.1700
Data Index: 7387101 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8015. Min Act: -0.1700
Data Index: 3912931 (Open Web Text)
Max Activating Token Index: 788
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.8015. Min Act: -0.1700
Data Index: 8781674 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.7702. Min Act: -0.1700
Data Index: 2725440 (Open Web Text)
Max Activating Token Index: 223
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.7702. Min Act: -0.1700
Data Index: 1741532 (Open Web Text)
Max Activating Token Index: 978
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.6765. Min Act: -0.1700
Data Index: 3392974 (Open Web Text)
Max Activating Token Index: 790
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.6765. Min Act: -0.1700
Data Index: 8334569 (Open Web Text)
Max Activating Token Index: 629
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.6452. Min Act: -0.1700
Data Index: 7584 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.6452. Min Act: -0.1700
Data Index: 5245417 (Open Web Text)
Max Activating Token Index: 258
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.3015. Min Range: -7.3015
Max Act: 6.6140. Min Act: -0.1700
Data Index: 7904975 (Open Web Text)
Max Activating Token Index: 746
Click toggle to see full text
Truncated
Full Text #19