Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 585 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.4478. Min Act: -0.1700
Data Index: 5539861 (Open Web Text)
Max Activating Token Index: 190
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.3853. Min Act: -0.1700
Data Index: 6246423 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.3853. Min Act: -0.1700
Data Index: 551158 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.3228. Min Act: -0.1700
Data Index: 2078807 (Open Web Text)
Max Activating Token Index: 559
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.2603. Min Act: -0.1700
Data Index: 4187413 (Open Web Text)
Max Activating Token Index: 449
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.3228. Min Act: -0.1700
Data Index: 3927403 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.1353. Min Act: -0.1700
Data Index: 3337156 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.1978. Min Act: -0.1700
Data Index: 2968031 (Open Web Text)
Max Activating Token Index: 636
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.1353. Min Act: -0.1700
Data Index: 4314142 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.1353. Min Act: -0.1700
Data Index: 741078 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.1353. Min Act: -0.1700
Data Index: 8655574 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.0728. Min Act: -0.1700
Data Index: 5609667 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.0728. Min Act: -0.1700
Data Index: 8549450 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.0103. Min Act: -0.1700
Data Index: 3355065 (Open Web Text)
Max Activating Token Index: 129
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.0103. Min Act: -0.1700
Data Index: 4055549 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4478. Min Range: -8.4478
Max Act: 8.0103. Min Act: -0.1700
Data Index: 102115 (Open Web Text)
Max Activating Token Index: 78
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4478. Min Range: -8.4478
Max Act: 7.9478. Min Act: -0.1700
Data Index: 1048108 (Open Web Text)
Max Activating Token Index: 913
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4478. Min Range: -8.4478
Max Act: 7.9478. Min Act: -0.1700
Data Index: 1728362 (Open Web Text)
Max Activating Token Index: 378
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4478. Min Range: -8.4478
Max Act: 7.9478. Min Act: -0.1700
Data Index: 3657900 (Open Web Text)
Max Activating Token Index: 512
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4478. Min Range: -8.4478
Max Act: 7.9478. Min Act: -0.1700
Data Index: 24651 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19