Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3272 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.4894. Min Act: -0.1700
Data Index: 7414949 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3644. Min Act: -0.1700
Data Index: 5339848 (Open Web Text)
Max Activating Token Index: 111
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3644. Min Act: -0.1700
Data Index: 5590315 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3644. Min Act: -0.1700
Data Index: 7445897 (Open Web Text)
Max Activating Token Index: 234
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 7850785 (Open Web Text)
Max Activating Token Index: 346
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 1980670 (Open Web Text)
Max Activating Token Index: 279
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 7994819 (Open Web Text)
Max Activating Token Index: 187
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 918412 (Open Web Text)
Max Activating Token Index: 899
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 7093783 (Open Web Text)
Max Activating Token Index: 502
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 1167550 (Open Web Text)
Max Activating Token Index: 452
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 4374610 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 7346472 (Open Web Text)
Max Activating Token Index: 743
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3332. Min Act: -0.1700
Data Index: 1471647 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3019. Min Act: -0.1700
Data Index: 2561569 (Open Web Text)
Max Activating Token Index: 835
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3019. Min Act: -0.1700
Data Index: 7135484 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3019. Min Act: -0.1700
Data Index: 7093790 (Open Web Text)
Max Activating Token Index: 224
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3019. Min Act: -0.1700
Data Index: 5676577 (Open Web Text)
Max Activating Token Index: 89
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3019. Min Act: -0.1700
Data Index: 5656271 (Open Web Text)
Max Activating Token Index: 701
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.3019. Min Act: -0.1700
Data Index: 1623915 (Open Web Text)
Max Activating Token Index: 699
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.4894. Min Range: -6.4894
Max Act: 6.2707. Min Act: -0.1700
Data Index: 6919373 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #19