Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3730 in Layer 43
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.8426. Min Act: -0.1700
Data Index: 7429001 (Open Web Text)
Max Activating Token Index: 477
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.7801. Min Act: -0.1700
Data Index: 8003584 (Open Web Text)
Max Activating Token Index: 785
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.6551. Min Act: -0.1700
Data Index: 3255683 (Open Web Text)
Max Activating Token Index: 852
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.6551. Min Act: -0.1700
Data Index: 3240134 (Open Web Text)
Max Activating Token Index: 952
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.6238. Min Act: -0.1700
Data Index: 3459326 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.5926. Min Act: -0.1700
Data Index: 6795833 (Open Web Text)
Max Activating Token Index: 597
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.5926. Min Act: -0.1700
Data Index: 1730070 (Open Web Text)
Max Activating Token Index: 648
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.5301. Min Act: -0.1700
Data Index: 7614017 (Open Web Text)
Max Activating Token Index: 415
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.5301. Min Act: -0.1700
Data Index: 5935511 (Open Web Text)
Max Activating Token Index: 679
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.5301. Min Act: -0.1700
Data Index: 2181917 (Open Web Text)
Max Activating Token Index: 226
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.4988. Min Act: -0.1700
Data Index: 3047068 (Open Web Text)
Max Activating Token Index: 510
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.4988. Min Act: -0.1700
Data Index: 3923953 (Open Web Text)
Max Activating Token Index: 941
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.4988. Min Act: -0.1700
Data Index: 3633798 (Open Web Text)
Max Activating Token Index: 213
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.4676. Min Act: -0.1700
Data Index: 1195145 (Open Web Text)
Max Activating Token Index: 172
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.4051. Min Act: -0.1700
Data Index: 4229871 (Open Web Text)
Max Activating Token Index: 750
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.4363. Min Act: -0.1700
Data Index: 8406337 (Open Web Text)
Max Activating Token Index: 898
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.3738. Min Act: -0.1700
Data Index: 7529674 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.3738. Min Act: -0.1700
Data Index: 136458 (Open Web Text)
Max Activating Token Index: 860
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.3113. Min Act: -0.1700
Data Index: 13704 (Open Web Text)
Max Activating Token Index: 708
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8426. Min Range: -7.8426
Max Act: 7.3426. Min Act: -0.1700
Data Index: 8131045 (Open Web Text)
Max Activating Token Index: 942
Click toggle to see full text
Truncated
Full Text #19