Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1798 in Layer 28
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.9657. Min Act: -0.1700
Data Index: 2492582 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.8407. Min Act: -0.1700
Data Index: 164920 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.8407. Min Act: -0.1700
Data Index: 913903 (Open Web Text)
Max Activating Token Index: 490
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.7782. Min Act: -0.1700
Data Index: 2854715 (Open Web Text)
Max Activating Token Index: 319
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.6220. Min Act: -0.1700
Data Index: 1347572 (Open Web Text)
Max Activating Token Index: 733
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.6220. Min Act: -0.1700
Data Index: 4967641 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.5595. Min Act: -0.1700
Data Index: 6077925 (Open Web Text)
Max Activating Token Index: 251
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4657. Min Act: -0.1700
Data Index: 5570002 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4032. Min Act: -0.1700
Data Index: 4494147 (Open Web Text)
Max Activating Token Index: 656
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4345. Min Act: -0.1700
Data Index: 4170697 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4345. Min Act: -0.1700
Data Index: 5185413 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4032. Min Act: -0.1700
Data Index: 253196 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4032. Min Act: -0.1700
Data Index: 3826043 (Open Web Text)
Max Activating Token Index: 715
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4032. Min Act: -0.1700
Data Index: 8189965 (Open Web Text)
Max Activating Token Index: 507
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.4032. Min Act: -0.1700
Data Index: 4554900 (Open Web Text)
Max Activating Token Index: 142
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.3720. Min Act: -0.1700
Data Index: 3552171 (Open Web Text)
Max Activating Token Index: 383
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.3095. Min Act: -0.1700
Data Index: 2922851 (Open Web Text)
Max Activating Token Index: 778
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.2782. Min Act: -0.1700
Data Index: 8403558 (Open Web Text)
Max Activating Token Index: 288
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.3095. Min Act: -0.1700
Data Index: 8230020 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9657. Min Range: -6.9657
Max Act: 6.2470. Min Act: -0.1700
Data Index: 5462780 (Open Web Text)
Max Activating Token Index: 906
Click toggle to see full text
Truncated
Full Text #19