Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3890 in Layer 16
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2315. Min Range: -4.2315
Max Act: 4.2315. Min Act: -0.1700
Data Index: 6806185 (Open Web Text)
Max Activating Token Index: 217
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2315. Min Range: -4.2315
Max Act: 4.1065. Min Act: -0.1700
Data Index: 4079944 (Open Web Text)
Max Activating Token Index: 756
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.8564. Min Act: -0.1700
Data Index: 6145637 (Open Web Text)
Max Activating Token Index: 869
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.8408. Min Act: -0.1700
Data Index: 3539934 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.8251. Min Act: -0.1700
Data Index: 2628803 (Open Web Text)
Max Activating Token Index: 660
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.8095. Min Act: -0.1700
Data Index: 8145640 (Open Web Text)
Max Activating Token Index: 435
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.7938. Min Act: -0.1700
Data Index: 827233 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.7782. Min Act: -0.1700
Data Index: 4207029 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.7782. Min Act: -0.1700
Data Index: 600321 (Open Web Text)
Max Activating Token Index: 907
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.7313. Min Act: -0.1700
Data Index: 4238939 (Open Web Text)
Max Activating Token Index: 865
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.7156. Min Act: -0.1700
Data Index: 1443285 (Open Web Text)
Max Activating Token Index: 698
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.7000. Min Act: -0.1700
Data Index: 8440940 (Open Web Text)
Max Activating Token Index: 955
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6687. Min Act: -0.1700
Data Index: 4969800 (Open Web Text)
Max Activating Token Index: 647
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6531. Min Act: -0.1700
Data Index: 8486898 (Open Web Text)
Max Activating Token Index: 716
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6374. Min Act: -0.1700
Data Index: 6571967 (Open Web Text)
Max Activating Token Index: 705
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6218. Min Act: -0.1700
Data Index: 2989663 (Open Web Text)
Max Activating Token Index: 368
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6218. Min Act: -0.1700
Data Index: 4192603 (Open Web Text)
Max Activating Token Index: 963
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6218. Min Act: -0.1700
Data Index: 8341886 (Open Web Text)
Max Activating Token Index: 152
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.5905. Min Act: -0.1700
Data Index: 5491716 (Open Web Text)
Max Activating Token Index: 453
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2315. Min Range: -4.2315
Max Act: 3.6061. Min Act: -0.1700
Data Index: 6769895 (Open Web Text)
Max Activating Token Index: 634
Click toggle to see full text
Truncated
Full Text #19