Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5392 in Layer 8
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.0710. Min Range: -6.0710
Max Act: 6.0710. Min Act: -0.1700
Data Index: 4257690 (Open Web Text)
Max Activating Token Index: 770
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.9773. Min Act: -0.1700
Data Index: 2796564 (Open Web Text)
Max Activating Token Index: 741
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.9773. Min Act: -0.1700
Data Index: 1541355 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.8835. Min Act: -0.1700
Data Index: 99428 (Open Web Text)
Max Activating Token Index: 720
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.8210. Min Act: -0.1700
Data Index: 3870572 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.8210. Min Act: -0.1700
Data Index: 3473008 (Open Web Text)
Max Activating Token Index: 670
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.8210. Min Act: -0.1700
Data Index: 8756505 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7898. Min Act: -0.1700
Data Index: 3182702 (Open Web Text)
Max Activating Token Index: 355
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.8210. Min Act: -0.1700
Data Index: 4778184 (Open Web Text)
Max Activating Token Index: 665
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7898. Min Act: -0.1700
Data Index: 7455064 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7898. Min Act: -0.1700
Data Index: 6553926 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7898. Min Act: -0.1700
Data Index: 3473007 (Open Web Text)
Max Activating Token Index: 517
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7898. Min Act: -0.1700
Data Index: 4449033 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7585. Min Act: -0.1700
Data Index: 2973821 (Open Web Text)
Max Activating Token Index: 792
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7585. Min Act: -0.1700
Data Index: 8722459 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7585. Min Act: -0.1700
Data Index: 3288633 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6490875 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7273. Min Act: -0.1700
Data Index: 1571721 (Open Web Text)
Max Activating Token Index: 159
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7273. Min Act: -0.1700
Data Index: 3480156 (Open Web Text)
Max Activating Token Index: 146
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.0710. Min Range: -6.0710
Max Act: 5.7273. Min Act: -0.1700
Data Index: 6915886 (Open Web Text)
Max Activating Token Index: 372
Click toggle to see full text
Truncated
Full Text #19