Model: GPT-2 Medium: 24 Layers, 4096 Neurons per Layer
Dataset: Open Web Text
Neuron 2783 in Layer 1
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-medium')
Text #0
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8736. Min Act: -0.1700
Data Index: 5928114 (Open Web Text)
Max Activating Token Index: 846
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8481. Min Act: -0.1700
Data Index: 6982694 (Open Web Text)
Max Activating Token Index: 832
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8144. Min Act: -0.1700
Data Index: 32960 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8144. Min Act: -0.1700
Data Index: 3302340 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8144. Min Act: -0.1700
Data Index: 4617810 (Open Web Text)
Max Activating Token Index: 821
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8144. Min Act: -0.1700
Data Index: 490995 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8144. Min Act: -0.1700
Data Index: 2970332 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8059. Min Act: -0.1700
Data Index: 6115154 (Open Web Text)
Max Activating Token Index: 849
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7976. Min Act: -0.1700
Data Index: 3970044 (Open Web Text)
Max Activating Token Index: 830
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8059. Min Act: -0.1700
Data Index: 280027 (Open Web Text)
Max Activating Token Index: 826
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.8059. Min Act: -0.1700
Data Index: 8831043 (Open Web Text)
Max Activating Token Index: 862
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7976. Min Act: -0.1700
Data Index: 4762647 (Open Web Text)
Max Activating Token Index: 838
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7976. Min Act: -0.1700
Data Index: 1857437 (Open Web Text)
Max Activating Token Index: 861
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7808. Min Act: -0.1700
Data Index: 4026945 (Open Web Text)
Max Activating Token Index: 871
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7976. Min Act: -0.1700
Data Index: 7005020 (Open Web Text)
Max Activating Token Index: 817
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7808. Min Act: -0.1700
Data Index: 7913916 (Open Web Text)
Max Activating Token Index: 842
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7725. Min Act: -0.1700
Data Index: 794157 (Open Web Text)
Max Activating Token Index: 840
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7808. Min Act: -0.1700
Data Index: 4746680 (Open Web Text)
Max Activating Token Index: 822
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7892. Min Act: -0.1700
Data Index: 1002755 (Open Web Text)
Max Activating Token Index: 850
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 0.8736. Min Range: -0.8736
Max Act: 0.7808. Min Act: -0.1700
Data Index: 2866069 (Open Web Text)
Max Activating Token Index: 851
Click toggle to see full text
Truncated
Full Text #19