Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1433 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0603. Min Range: -6.0603
Max Act: 6.0603. Min Act: -0.1700
Data Index: 8287219 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.8728. Min Act: -0.1700
Data Index: 6820868 (Open Web Text)
Max Activating Token Index: 191
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.8415. Min Act: -0.1700
Data Index: 8269936 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.7790. Min Act: -0.1700
Data Index: 4597938 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.7478. Min Act: -0.1700
Data Index: 6649676 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.7478. Min Act: -0.1700
Data Index: 4599285 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.7478. Min Act: -0.1700
Data Index: 5194213 (Open Web Text)
Max Activating Token Index: 94
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.7165. Min Act: -0.1700
Data Index: 4727108 (Open Web Text)
Max Activating Token Index: 322
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.7165. Min Act: -0.1700
Data Index: 7350827 (Open Web Text)
Max Activating Token Index: 961
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.6853. Min Act: -0.1700
Data Index: 3031976 (Open Web Text)
Max Activating Token Index: 866
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.6540. Min Act: -0.1700
Data Index: 5266598 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.6853. Min Act: -0.1700
Data Index: 7226113 (Open Web Text)
Max Activating Token Index: 1005
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.6853. Min Act: -0.1700
Data Index: 478059 (Open Web Text)
Max Activating Token Index: 982
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.5915. Min Act: -0.1700
Data Index: 1631248 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.6228. Min Act: -0.1700
Data Index: 5055236 (Open Web Text)
Max Activating Token Index: 544
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.6228. Min Act: -0.1700
Data Index: 4807870 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.5915. Min Act: -0.1700
Data Index: 8409916 (Open Web Text)
Max Activating Token Index: 870
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.5603. Min Act: -0.1700
Data Index: 4075750 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.5603. Min Act: -0.1700
Data Index: 7435204 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0603. Min Range: -6.0603
Max Act: 5.5603. Min Act: -0.1700
Data Index: 1700489 (Open Web Text)
Max Activating Token Index: 1002
Click toggle to see full text
Truncated
Full Text #19