Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3485 in Layer 39
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.9577. Min Act: -0.1700
Data Index: 5843009 (Open Web Text)
Max Activating Token Index: 315
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.8952. Min Act: -0.1700
Data Index: 2674990 (Open Web Text)
Max Activating Token Index: 387
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.8640. Min Act: -0.1700
Data Index: 4889957 (Open Web Text)
Max Activating Token Index: 366
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.8015. Min Act: -0.1700
Data Index: 337322 (Open Web Text)
Max Activating Token Index: 281
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.7702. Min Act: -0.1700
Data Index: 648894 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.7077. Min Act: -0.1700
Data Index: 3131798 (Open Web Text)
Max Activating Token Index: 520
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.6452. Min Act: -0.1700
Data Index: 6599892 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.5827. Min Act: -0.1700
Data Index: 3944921 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.5827. Min Act: -0.1700
Data Index: 7974526 (Open Web Text)
Max Activating Token Index: 434
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.4577. Min Act: -0.1700
Data Index: 1908463 (Open Web Text)
Max Activating Token Index: 303
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.4265. Min Act: -0.1700
Data Index: 8675633 (Open Web Text)
Max Activating Token Index: 816
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3952. Min Act: -0.1700
Data Index: 5546356 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3640. Min Act: -0.1700
Data Index: 1111721 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3640. Min Act: -0.1700
Data Index: 403868 (Open Web Text)
Max Activating Token Index: 252
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3640. Min Act: -0.1700
Data Index: 2566379 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3327. Min Act: -0.1700
Data Index: 3359017 (Open Web Text)
Max Activating Token Index: 1016
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3015. Min Act: -0.1700
Data Index: 6817488 (Open Web Text)
Max Activating Token Index: 799
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3015. Min Act: -0.1700
Data Index: 5295894 (Open Web Text)
Max Activating Token Index: 352
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3015. Min Act: -0.1700
Data Index: 4913746 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9577. Min Range: -6.9577
Max Act: 6.3015. Min Act: -0.1700
Data Index: 344261 (Open Web Text)
Max Activating Token Index: 411
Click toggle to see full text
Truncated
Full Text #19