Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2965 in Layer 3
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2388. Min Act: -0.1700
Data Index: 5618502 (Open Web Text)
Max Activating Token Index: 1017
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2388. Min Act: -0.1700
Data Index: 8367538 (Open Web Text)
Max Activating Token Index: 940
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2388. Min Act: -0.1700
Data Index: 3803306 (Open Web Text)
Max Activating Token Index: 370
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2388. Min Act: -0.1700
Data Index: 6546505 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2388. Min Act: -0.1700
Data Index: 2491576 (Open Web Text)
Max Activating Token Index: 283
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2075. Min Act: -0.1700
Data Index: 2610669 (Open Web Text)
Max Activating Token Index: 58
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2075. Min Act: -0.1700
Data Index: 2696463 (Open Web Text)
Max Activating Token Index: 294
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2075. Min Act: -0.1700
Data Index: 7501426 (Open Web Text)
Max Activating Token Index: 489
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2075. Min Act: -0.1700
Data Index: 2696462 (Open Web Text)
Max Activating Token Index: 729
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.2075. Min Act: -0.1700
Data Index: 3773713 (Open Web Text)
Max Activating Token Index: 462
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1763. Min Act: -0.1700
Data Index: 7123353 (Open Web Text)
Max Activating Token Index: 965
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1763. Min Act: -0.1700
Data Index: 3145471 (Open Web Text)
Max Activating Token Index: 183
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1763. Min Act: -0.1700
Data Index: 4924801 (Open Web Text)
Max Activating Token Index: 609
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1763. Min Act: -0.1700
Data Index: 1305085 (Open Web Text)
Max Activating Token Index: 905
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1763. Min Act: -0.1700
Data Index: 3107332 (Open Web Text)
Max Activating Token Index: 44
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1763. Min Act: -0.1700
Data Index: 2491575 (Open Web Text)
Max Activating Token Index: 112
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1450. Min Act: -0.1700
Data Index: 4014700 (Open Web Text)
Max Activating Token Index: 827
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1450. Min Act: -0.1700
Data Index: 4364891 (Open Web Text)
Max Activating Token Index: 911
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1450. Min Act: -0.1700
Data Index: 1166915 (Open Web Text)
Max Activating Token Index: 96
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.2388. Min Range: -4.2388
Max Act: 4.1137. Min Act: -0.1700
Data Index: 3400147 (Open Web Text)
Max Activating Token Index: 719
Click toggle to see full text
Truncated
Full Text #19