Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2564 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.4673. Min Act: -0.1700
Data Index: 5592807 (Open Web Text)
Max Activating Token Index: 547
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.4048. Min Act: -0.1700
Data Index: 5994408 (Open Web Text)
Max Activating Token Index: 219
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.3736. Min Act: -0.1700
Data Index: 7644238 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.3736. Min Act: -0.1700
Data Index: 5592815 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.3423. Min Act: -0.1700
Data Index: 5592814 (Open Web Text)
Max Activating Token Index: 742
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.2173. Min Act: -0.1700
Data Index: 5726510 (Open Web Text)
Max Activating Token Index: 41
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.1861. Min Act: -0.1700
Data Index: 5726519 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.1548. Min Act: -0.1700
Data Index: 4523790 (Open Web Text)
Max Activating Token Index: 697
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.1236. Min Act: -0.1700
Data Index: 5726509 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0923. Min Act: -0.1700
Data Index: 5726518 (Open Web Text)
Max Activating Token Index: 624
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0923. Min Act: -0.1700
Data Index: 5994409 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0611. Min Act: -0.1700
Data Index: 722599 (Open Web Text)
Max Activating Token Index: 371
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0611. Min Act: -0.1700
Data Index: 1173529 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0611. Min Act: -0.1700
Data Index: 5595100 (Open Web Text)
Max Activating Token Index: 2
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0298. Min Act: -0.1700
Data Index: 6621416 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.4673. Min Range: -5.4673
Max Act: 5.0298. Min Act: -0.1700
Data Index: 231468 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.4673. Min Range: -5.4673
Max Act: 4.9986. Min Act: -0.1700
Data Index: 4032381 (Open Web Text)
Max Activating Token Index: 935
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.4673. Min Range: -5.4673
Max Act: 4.9986. Min Act: -0.1700
Data Index: 476507 (Open Web Text)
Max Activating Token Index: 886
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.4673. Min Range: -5.4673
Max Act: 4.9986. Min Act: -0.1700
Data Index: 3005936 (Open Web Text)
Max Activating Token Index: 726
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.4673. Min Range: -5.4673
Max Act: 4.9986. Min Act: -0.1700
Data Index: 995435 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #19