Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5403 in Layer 25
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.9457. Min Act: -0.1700
Data Index: 7612255 (Open Web Text)
Max Activating Token Index: 255
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.9457. Min Act: -0.1700
Data Index: 3868518 (Open Web Text)
Max Activating Token Index: 444
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.8832. Min Act: -0.1700
Data Index: 1158448 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.8519. Min Act: -0.1700
Data Index: 931073 (Open Web Text)
Max Activating Token Index: 399
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7894. Min Act: -0.1700
Data Index: 1906559 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8741961 (Open Web Text)
Max Activating Token Index: 576
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8716939 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8454046 (Open Web Text)
Max Activating Token Index: 598
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 1746751 (Open Web Text)
Max Activating Token Index: 358
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 8244854 (Open Web Text)
Max Activating Token Index: 295
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 2992853 (Open Web Text)
Max Activating Token Index: 666
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 6793763 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 8671607 (Open Web Text)
Max Activating Token Index: 587
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 5478487 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 7978694 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 7844022 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 8616872 (Open Web Text)
Max Activating Token Index: 855
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7269. Min Act: -0.1700
Data Index: 8393706 (Open Web Text)
Max Activating Token Index: 105
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.7582. Min Act: -0.1700
Data Index: 4027650 (Open Web Text)
Max Activating Token Index: 74
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.9457. Min Range: -6.9457
Max Act: 6.6957. Min Act: -0.1700
Data Index: 3293866 (Open Web Text)
Max Activating Token Index: 327
Click toggle to see full text
Truncated
Full Text #19