Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3972 in Layer 45
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.1277. Min Range: -7.1277
Max Act: 7.1277. Min Act: -0.1700
Data Index: 7552843 (Open Web Text)
Max Activating Token Index: 625
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.1277. Min Range: -7.1277
Max Act: 7.0964. Min Act: -0.1700
Data Index: 3655666 (Open Web Text)
Max Activating Token Index: 299
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.1277. Min Range: -7.1277
Max Act: 7.0027. Min Act: -0.1700
Data Index: 1853188 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.9089. Min Act: -0.1700
Data Index: 7807499 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.8777. Min Act: -0.1700
Data Index: 3211290 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.9089. Min Act: -0.1700
Data Index: 1650747 (Open Web Text)
Max Activating Token Index: 937
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.8152. Min Act: -0.1700
Data Index: 6260615 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.8152. Min Act: -0.1700
Data Index: 1623603 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.8152. Min Act: -0.1700
Data Index: 4738822 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.8152. Min Act: -0.1700
Data Index: 3204181 (Open Web Text)
Max Activating Token Index: 503
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.7527. Min Act: -0.1700
Data Index: 1076447 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.7214. Min Act: -0.1700
Data Index: 7610452 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.7214. Min Act: -0.1700
Data Index: 4513722 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6902. Min Act: -0.1700
Data Index: 2010883 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6902. Min Act: -0.1700
Data Index: 5746810 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6902. Min Act: -0.1700
Data Index: 7077777 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6902. Min Act: -0.1700
Data Index: 994951 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6589. Min Act: -0.1700
Data Index: 6766166 (Open Web Text)
Max Activating Token Index: 969
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6902. Min Act: -0.1700
Data Index: 2843963 (Open Web Text)
Max Activating Token Index: 723
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.1277. Min Range: -7.1277
Max Act: 6.6277. Min Act: -0.1700
Data Index: 642550 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #19