Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 448 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7863. Min Act: -0.1700
Data Index: 787082 (Open Web Text)
Max Activating Token Index: 163
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7863. Min Act: -0.1700
Data Index: 4826443 (Open Web Text)
Max Activating Token Index: 103
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7704. Min Act: -0.1700
Data Index: 401983 (Open Web Text)
Max Activating Token Index: 332
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7544. Min Act: -0.1700
Data Index: 8759883 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7704. Min Act: -0.1700
Data Index: 5664208 (Open Web Text)
Max Activating Token Index: 989
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7544. Min Act: -0.1700
Data Index: 6862666 (Open Web Text)
Max Activating Token Index: 595
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7544. Min Act: -0.1700
Data Index: 2646071 (Open Web Text)
Max Activating Token Index: 122
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7384. Min Act: -0.1700
Data Index: 4377017 (Open Web Text)
Max Activating Token Index: 845
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7225. Min Act: -0.1700
Data Index: 7857820 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7065. Min Act: -0.1700
Data Index: 2952873 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7225. Min Act: -0.1700
Data Index: 444264 (Open Web Text)
Max Activating Token Index: 491
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7225. Min Act: -0.1700
Data Index: 5628181 (Open Web Text)
Max Activating Token Index: 428
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7065. Min Act: -0.1700
Data Index: 5280256 (Open Web Text)
Max Activating Token Index: 233
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7065. Min Act: -0.1700
Data Index: 2239025 (Open Web Text)
Max Activating Token Index: 594
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.6745. Min Act: -0.1700
Data Index: 734792 (Open Web Text)
Max Activating Token Index: 933
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7225. Min Act: -0.1700
Data Index: 724227 (Open Web Text)
Max Activating Token Index: 542
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.7065. Min Act: -0.1700
Data Index: 6604530 (Open Web Text)
Max Activating Token Index: 759
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.6745. Min Act: -0.1700
Data Index: 6997523 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.6745. Min Act: -0.1700
Data Index: 4299445 (Open Web Text)
Max Activating Token Index: 725
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 2.7863. Min Range: -2.7863
Max Act: 2.6905. Min Act: -0.1700
Data Index: 7196785 (Open Web Text)
Max Activating Token Index: 500
Click toggle to see full text
Truncated
Full Text #19