Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 65 in Layer 29
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.9078. Min Act: -0.1700
Data Index: 1203901 (Open Web Text)
Max Activating Token Index: 488
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.6891. Min Act: -0.1700
Data Index: 5410416 (Open Web Text)
Max Activating Token Index: 514
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.5953. Min Act: -0.1700
Data Index: 5936013 (Open Web Text)
Max Activating Token Index: 954
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.5016. Min Act: -0.1700
Data Index: 1177494 (Open Web Text)
Max Activating Token Index: 561
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.4391. Min Act: -0.1700
Data Index: 335056 (Open Web Text)
Max Activating Token Index: 931
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.4391. Min Act: -0.1700
Data Index: 3928032 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.4391. Min Act: -0.1700
Data Index: 3951664 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5870992 (Open Web Text)
Max Activating Token Index: 760
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.3766. Min Act: -0.1700
Data Index: 5084666 (Open Web Text)
Max Activating Token Index: 590
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.3766. Min Act: -0.1700
Data Index: 8508829 (Open Web Text)
Max Activating Token Index: 771
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.3453. Min Act: -0.1700
Data Index: 5364255 (Open Web Text)
Max Activating Token Index: 623
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.3141. Min Act: -0.1700
Data Index: 8752288 (Open Web Text)
Max Activating Token Index: 445
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.3141. Min Act: -0.1700
Data Index: 2803732 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2828. Min Act: -0.1700
Data Index: 2411880 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2828. Min Act: -0.1700
Data Index: 3098396 (Open Web Text)
Max Activating Token Index: 35
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2828. Min Act: -0.1700
Data Index: 511840 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2828. Min Act: -0.1700
Data Index: 1843306 (Open Web Text)
Max Activating Token Index: 494
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2516. Min Act: -0.1700
Data Index: 7146792 (Open Web Text)
Max Activating Token Index: 709
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2516. Min Act: -0.1700
Data Index: 3061341 (Open Web Text)
Max Activating Token Index: 227
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 5.9078. Min Range: -5.9078
Max Act: 5.2516. Min Act: -0.1700
Data Index: 3364788 (Open Web Text)
Max Activating Token Index: 225
Click toggle to see full text
Truncated
Full Text #19