Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1728 in Layer 7
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0997. Min Range: -6.0997
Max Act: 6.0997. Min Act: -0.1700
Data Index: 1094243 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0997. Min Range: -6.0997
Max Act: 6.0685. Min Act: -0.1700
Data Index: 735521 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0997. Min Range: -6.0997
Max Act: 6.0060. Min Act: -0.1700
Data Index: 4489271 (Open Web Text)
Max Activating Token Index: 610
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 5742569 (Open Web Text)
Max Activating Token Index: 618
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 561134 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 16010 (Open Web Text)
Max Activating Token Index: 485
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 3518959 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 6943149 (Open Web Text)
Max Activating Token Index: 419
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 5016819 (Open Web Text)
Max Activating Token Index: 612
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9747. Min Act: -0.1700
Data Index: 5614894 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9435. Min Act: -0.1700
Data Index: 6978835 (Open Web Text)
Max Activating Token Index: 431
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9435. Min Act: -0.1700
Data Index: 1654728 (Open Web Text)
Max Activating Token Index: 276
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9435. Min Act: -0.1700
Data Index: 2000651 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9435. Min Act: -0.1700
Data Index: 7325859 (Open Web Text)
Max Activating Token Index: 349
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9435. Min Act: -0.1700
Data Index: 609300 (Open Web Text)
Max Activating Token Index: 338
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9122. Min Act: -0.1700
Data Index: 3965801 (Open Web Text)
Max Activating Token Index: 169
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9122. Min Act: -0.1700
Data Index: 16857 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9122. Min Act: -0.1700
Data Index: 7034799 (Open Web Text)
Max Activating Token Index: 1014
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9122. Min Act: -0.1700
Data Index: 5458240 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0997. Min Range: -6.0997
Max Act: 5.9122. Min Act: -0.1700
Data Index: 3515870 (Open Web Text)
Max Activating Token Index: 432
Click toggle to see full text
Truncated
Full Text #19