Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3038 in Layer 19
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.8959. Min Act: -0.1700
Data Index: 4171389 (Open Web Text)
Max Activating Token Index: 828
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.8646. Min Act: -0.1700
Data Index: 4884089 (Open Web Text)
Max Activating Token Index: 918
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.7864. Min Act: -0.1700
Data Index: 7171725 (Open Web Text)
Max Activating Token Index: 473
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.7551. Min Act: -0.1700
Data Index: 679183 (Open Web Text)
Max Activating Token Index: 797
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.7239. Min Act: -0.1700
Data Index: 3487936 (Open Web Text)
Max Activating Token Index: 766
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6926. Min Act: -0.1700
Data Index: 490824 (Open Web Text)
Max Activating Token Index: 306
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6926. Min Act: -0.1700
Data Index: 8274776 (Open Web Text)
Max Activating Token Index: 287
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6769. Min Act: -0.1700
Data Index: 8035628 (Open Web Text)
Max Activating Token Index: 463
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6769. Min Act: -0.1700
Data Index: 3234131 (Open Web Text)
Max Activating Token Index: 644
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6613. Min Act: -0.1700
Data Index: 1412715 (Open Web Text)
Max Activating Token Index: 974
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6300. Min Act: -0.1700
Data Index: 4537027 (Open Web Text)
Max Activating Token Index: 814
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6456. Min Act: -0.1700
Data Index: 5298232 (Open Web Text)
Max Activating Token Index: 253
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6143. Min Act: -0.1700
Data Index: 6744927 (Open Web Text)
Max Activating Token Index: 761
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.6143. Min Act: -0.1700
Data Index: 1123561 (Open Web Text)
Max Activating Token Index: 181
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.5987. Min Act: -0.1700
Data Index: 8029181 (Open Web Text)
Max Activating Token Index: 970
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.5987. Min Act: -0.1700
Data Index: 6053108 (Open Web Text)
Max Activating Token Index: 897
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.5987. Min Act: -0.1700
Data Index: 920035 (Open Web Text)
Max Activating Token Index: 132
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.5987. Min Act: -0.1700
Data Index: 1778137 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.5987. Min Act: -0.1700
Data Index: 1745013 (Open Web Text)
Max Activating Token Index: 29
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 3.8959. Min Range: -3.8959
Max Act: 3.5987. Min Act: -0.1700
Data Index: 8505541 (Open Web Text)
Max Activating Token Index: 823
Click toggle to see full text
Truncated
Full Text #19