Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3658 in Layer 46
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.5294. Min Act: -0.1700
Data Index: 4583281 (Open Web Text)
Max Activating Token Index: 471
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.2169. Min Act: -0.1700
Data Index: 6074695 (Open Web Text)
Max Activating Token Index: 956
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.2169. Min Act: -0.1700
Data Index: 274832 (Open Web Text)
Max Activating Token Index: 932
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.1544. Min Act: -0.1700
Data Index: 1634208 (Open Web Text)
Max Activating Token Index: 853
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.1232. Min Act: -0.1700
Data Index: 8688789 (Open Web Text)
Max Activating Token Index: 153
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.0919. Min Act: -0.1700
Data Index: 6046140 (Open Web Text)
Max Activating Token Index: 438
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.0919. Min Act: -0.1700
Data Index: 3728962 (Open Web Text)
Max Activating Token Index: 885
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.0919. Min Act: -0.1700
Data Index: 3507698 (Open Web Text)
Max Activating Token Index: 859
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.0607. Min Act: -0.1700
Data Index: 1080729 (Open Web Text)
Max Activating Token Index: 914
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.0294. Min Act: -0.1700
Data Index: 7308821 (Open Web Text)
Max Activating Token Index: 162
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.5294. Min Range: -7.5294
Max Act: 7.0294. Min Act: -0.1700
Data Index: 2056457 (Open Web Text)
Max Activating Token Index: 786
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.9982. Min Act: -0.1700
Data Index: 5840170 (Open Web Text)
Max Activating Token Index: 811
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.9669. Min Act: -0.1700
Data Index: 860072 (Open Web Text)
Max Activating Token Index: 363
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.9357. Min Act: -0.1700
Data Index: 3571011 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.9357. Min Act: -0.1700
Data Index: 3103908 (Open Web Text)
Max Activating Token Index: 631
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.8732. Min Act: -0.1700
Data Index: 1539896 (Open Web Text)
Max Activating Token Index: 664
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.8732. Min Act: -0.1700
Data Index: 7148559 (Open Web Text)
Max Activating Token Index: 126
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.8107. Min Act: -0.1700
Data Index: 4286957 (Open Web Text)
Max Activating Token Index: 677
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.8107. Min Act: -0.1700
Data Index: 8100854 (Open Web Text)
Max Activating Token Index: 506
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.5294. Min Range: -7.5294
Max Act: 6.7794. Min Act: -0.1700
Data Index: 8819202 (Open Web Text)
Max Activating Token Index: 923
Click toggle to see full text
Truncated
Full Text #19