Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3094 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.2478. Min Range: -7.2478
Max Act: 7.2478. Min Act: -0.1700
Data Index: 3275488 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.2478. Min Range: -7.2478
Max Act: 7.0603. Min Act: -0.1700
Data Index: 5332986 (Open Web Text)
Max Activating Token Index: 1010
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.9665. Min Act: -0.1700
Data Index: 6479505 (Open Web Text)
Max Activating Token Index: 775
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.8415. Min Act: -0.1700
Data Index: 1911929 (Open Web Text)
Max Activating Token Index: 779
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.7790. Min Act: -0.1700
Data Index: 7278400 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.7478. Min Act: -0.1700
Data Index: 1199086 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.7478. Min Act: -0.1700
Data Index: 720364 (Open Web Text)
Max Activating Token Index: 155
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.6853. Min Act: -0.1700
Data Index: 1646045 (Open Web Text)
Max Activating Token Index: 539
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.6853. Min Act: -0.1700
Data Index: 7474849 (Open Web Text)
Max Activating Token Index: 173
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.6228. Min Act: -0.1700
Data Index: 7313494 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.6540. Min Act: -0.1700
Data Index: 4907794 (Open Web Text)
Max Activating Token Index: 657
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.6228. Min Act: -0.1700
Data Index: 4311675 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.5915. Min Act: -0.1700
Data Index: 3898848 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.5915. Min Act: -0.1700
Data Index: 976427 (Open Web Text)
Max Activating Token Index: 461
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.5603. Min Act: -0.1700
Data Index: 7665974 (Open Web Text)
Max Activating Token Index: 550
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.5290. Min Act: -0.1700
Data Index: 3671939 (Open Web Text)
Max Activating Token Index: 310
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.5290. Min Act: -0.1700
Data Index: 737966 (Open Web Text)
Max Activating Token Index: 339
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.4978. Min Act: -0.1700
Data Index: 272249 (Open Web Text)
Max Activating Token Index: 80
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.4978. Min Act: -0.1700
Data Index: 1528843 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.2478. Min Range: -7.2478
Max Act: 6.4978. Min Act: -0.1700
Data Index: 369950 (Open Web Text)
Max Activating Token Index: 329
Click toggle to see full text
Truncated
Full Text #19