Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3664 in Layer 42
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.7352. Min Act: -0.1700
Data Index: 6320992 (Open Web Text)
Max Activating Token Index: 553
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.3290. Min Act: -0.1700
Data Index: 3282629 (Open Web Text)
Max Activating Token Index: 637
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.3290. Min Act: -0.1700
Data Index: 5989914 (Open Web Text)
Max Activating Token Index: 658
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.2665. Min Act: -0.1700
Data Index: 2561653 (Open Web Text)
Max Activating Token Index: 189
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.1727. Min Act: -0.1700
Data Index: 2028307 (Open Web Text)
Max Activating Token Index: 472
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.1415. Min Act: -0.1700
Data Index: 3903775 (Open Web Text)
Max Activating Token Index: 762
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.1102. Min Act: -0.1700
Data Index: 4424910 (Open Web Text)
Max Activating Token Index: 1004
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.0790. Min Act: -0.1700
Data Index: 8090237 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.0165. Min Act: -0.1700
Data Index: 1366436 (Open Web Text)
Max Activating Token Index: 671
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.7352. Min Range: -7.7352
Max Act: 7.0165. Min Act: -0.1700
Data Index: 2071022 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.9852. Min Act: -0.1700
Data Index: 8744754 (Open Web Text)
Max Activating Token Index: 668
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.9540. Min Act: -0.1700
Data Index: 378440 (Open Web Text)
Max Activating Token Index: 601
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.9227. Min Act: -0.1700
Data Index: 3330907 (Open Web Text)
Max Activating Token Index: 868
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.9227. Min Act: -0.1700
Data Index: 6152578 (Open Web Text)
Max Activating Token Index: 398
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.8915. Min Act: -0.1700
Data Index: 6152585 (Open Web Text)
Max Activating Token Index: 767
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.9540. Min Act: -0.1700
Data Index: 5831651 (Open Web Text)
Max Activating Token Index: 199
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.8915. Min Act: -0.1700
Data Index: 378453 (Open Web Text)
Max Activating Token Index: 394
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.8602. Min Act: -0.1700
Data Index: 7066171 (Open Web Text)
Max Activating Token Index: 892
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.8290. Min Act: -0.1700
Data Index: 7510559 (Open Web Text)
Max Activating Token Index: 344
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.7352. Min Range: -7.7352
Max Act: 6.8290. Min Act: -0.1700
Data Index: 7271388 (Open Web Text)
Max Activating Token Index: 936
Click toggle to see full text
Truncated
Full Text #19