Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3257 in Layer 24
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.5218. Min Range: -6.5218
Max Act: 6.5218. Min Act: -0.1700
Data Index: 5220950 (Open Web Text)
Max Activating Token Index: 917
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.5218. Min Range: -6.5218
Max Act: 6.2718. Min Act: -0.1700
Data Index: 7854400 (Open Web Text)
Max Activating Token Index: 739
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.5218. Min Range: -6.5218
Max Act: 6.0843. Min Act: -0.1700
Data Index: 3022540 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.5218. Min Range: -6.5218
Max Act: 6.0530. Min Act: -0.1700
Data Index: 3296062 (Open Web Text)
Max Activating Token Index: 555
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.5218. Min Range: -6.5218
Max Act: 6.0218. Min Act: -0.1700
Data Index: 1127577 (Open Web Text)
Max Activating Token Index: 168
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.9905. Min Act: -0.1700
Data Index: 7009955 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8655. Min Act: -0.1700
Data Index: 364391 (Open Web Text)
Max Activating Token Index: 896
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8655. Min Act: -0.1700
Data Index: 5102709 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8343. Min Act: -0.1700
Data Index: 3450201 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8343. Min Act: -0.1700
Data Index: 368208 (Open Web Text)
Max Activating Token Index: 983
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8030. Min Act: -0.1700
Data Index: 8447366 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8030. Min Act: -0.1700
Data Index: 334519 (Open Web Text)
Max Activating Token Index: 996
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.8030. Min Act: -0.1700
Data Index: 8253557 (Open Web Text)
Max Activating Token Index: 410
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7718. Min Act: -0.1700
Data Index: 7601148 (Open Web Text)
Max Activating Token Index: 622
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7718. Min Act: -0.1700
Data Index: 956792 (Open Web Text)
Max Activating Token Index: 454
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7718. Min Act: -0.1700
Data Index: 3266386 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7405. Min Act: -0.1700
Data Index: 7608662 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7093. Min Act: -0.1700
Data Index: 6489993 (Open Web Text)
Max Activating Token Index: 780
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7405. Min Act: -0.1700
Data Index: 7853210 (Open Web Text)
Max Activating Token Index: 734
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.5218. Min Range: -6.5218
Max Act: 5.7093. Min Act: -0.1700
Data Index: 3632683 (Open Web Text)
Max Activating Token Index: 900
Click toggle to see full text
Truncated
Full Text #19