Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 4138 in Layer 38
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.7438. Min Range: -8.7438
Max Act: 8.7438. Min Act: -0.1700
Data Index: 2481758 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.7438. Min Range: -8.7438
Max Act: 8.1813. Min Act: -0.1700
Data Index: 899121 (Open Web Text)
Max Activating Token Index: 47
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.7438. Min Range: -8.7438
Max Act: 8.1188. Min Act: -0.1700
Data Index: 7359488 (Open Web Text)
Max Activating Token Index: 524
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.9938. Min Act: -0.1700
Data Index: 1086471 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.7438. Min Range: -8.7438
Max Act: 8.0563. Min Act: -0.1700
Data Index: 8452839 (Open Web Text)
Max Activating Token Index: 608
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.9313. Min Act: -0.1700
Data Index: 1252003 (Open Web Text)
Max Activating Token Index: 531
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.9938. Min Act: -0.1700
Data Index: 5247635 (Open Web Text)
Max Activating Token Index: 336
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.9938. Min Act: -0.1700
Data Index: 3062127 (Open Web Text)
Max Activating Token Index: 765
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.8688. Min Act: -0.1700
Data Index: 8556456 (Open Web Text)
Max Activating Token Index: 981
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.8063. Min Act: -0.1700
Data Index: 1736458 (Open Web Text)
Max Activating Token Index: 393
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.8688. Min Act: -0.1700
Data Index: 706570 (Open Web Text)
Max Activating Token Index: 953
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.8063. Min Act: -0.1700
Data Index: 3230144 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.8063. Min Act: -0.1700
Data Index: 7884644 (Open Web Text)
Max Activating Token Index: 521
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.8063. Min Act: -0.1700
Data Index: 8663108 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.7438. Min Act: -0.1700
Data Index: 3110137 (Open Web Text)
Max Activating Token Index: 541
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.6813. Min Act: -0.1700
Data Index: 76819 (Open Web Text)
Max Activating Token Index: 880
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.7438. Min Act: -0.1700
Data Index: 4671778 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.7438. Min Act: -0.1700
Data Index: 7364696 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.7438. Min Act: -0.1700
Data Index: 3832349 (Open Web Text)
Max Activating Token Index: 800
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.7438. Min Range: -8.7438
Max Act: 7.7438. Min Act: -0.1700
Data Index: 4638071 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #19