Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 1390 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 8.4688. Min Range: -8.4688
Max Act: 8.4688. Min Act: -0.1700
Data Index: 4082800 (Open Web Text)
Max Activating Token Index: 407
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 8.4688. Min Range: -8.4688
Max Act: 8.1563. Min Act: -0.1700
Data Index: 5330159 (Open Web Text)
Max Activating Token Index: 654
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 8.4688. Min Range: -8.4688
Max Act: 8.0626. Min Act: -0.1700
Data Index: 4806423 (Open Web Text)
Max Activating Token Index: 128
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 8.4688. Min Range: -8.4688
Max Act: 8.0626. Min Act: -0.1700
Data Index: 7010820 (Open Web Text)
Max Activating Token Index: 867
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 8.4688. Min Range: -8.4688
Max Act: 8.0001. Min Act: -0.1700
Data Index: 253122 (Open Web Text)
Max Activating Token Index: 455
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.9376. Min Act: -0.1700
Data Index: 2352143 (Open Web Text)
Max Activating Token Index: 591
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.9063. Min Act: -0.1700
Data Index: 5009058 (Open Web Text)
Max Activating Token Index: 772
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.7813. Min Act: -0.1700
Data Index: 7505287 (Open Web Text)
Max Activating Token Index: 272
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.7813. Min Act: -0.1700
Data Index: 1268421 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.6876. Min Act: -0.1700
Data Index: 2488308 (Open Web Text)
Max Activating Token Index: 266
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5938. Min Act: -0.1700
Data Index: 391810 (Open Web Text)
Max Activating Token Index: 711
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5938. Min Act: -0.1700
Data Index: 5064068 (Open Web Text)
Max Activating Token Index: 350
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5626. Min Act: -0.1700
Data Index: 3358692 (Open Web Text)
Max Activating Token Index: 418
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5626. Min Act: -0.1700
Data Index: 5753327 (Open Web Text)
Max Activating Token Index: 922
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5313. Min Act: -0.1700
Data Index: 7026250 (Open Web Text)
Max Activating Token Index: 1022
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5001. Min Act: -0.1700
Data Index: 4256665 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5001. Min Act: -0.1700
Data Index: 5603031 (Open Web Text)
Max Activating Token Index: 878
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5001. Min Act: -0.1700
Data Index: 8052192 (Open Web Text)
Max Activating Token Index: 377
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5001. Min Act: -0.1700
Data Index: 8823974 (Open Web Text)
Max Activating Token Index: 519
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 8.4688. Min Range: -8.4688
Max Act: 7.5001. Min Act: -0.1700
Data Index: 2390006 (Open Web Text)
Max Activating Token Index: 813
Click toggle to see full text
Truncated
Full Text #19