Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 3112 in Layer 27
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.7320. Min Act: -0.1700
Data Index: 8569414 (Open Web Text)
Max Activating Token Index: 496
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.5757. Min Act: -0.1700
Data Index: 7965387 (Open Web Text)
Max Activating Token Index: 702
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.5132. Min Act: -0.1700
Data Index: 6357316 (Open Web Text)
Max Activating Token Index: 721
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.5132. Min Act: -0.1700
Data Index: 361459 (Open Web Text)
Max Activating Token Index: 675
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.4195. Min Act: -0.1700
Data Index: 1364940 (Open Web Text)
Max Activating Token Index: 663
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.3882. Min Act: -0.1700
Data Index: 4299612 (Open Web Text)
Max Activating Token Index: 749
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.3570. Min Act: -0.1700
Data Index: 5861497 (Open Web Text)
Max Activating Token Index: 516
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.3570. Min Act: -0.1700
Data Index: 7008835 (Open Web Text)
Max Activating Token Index: 864
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.3257. Min Act: -0.1700
Data Index: 342979 (Open Web Text)
Max Activating Token Index: 296
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2945. Min Act: -0.1700
Data Index: 7965388 (Open Web Text)
Max Activating Token Index: 198
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2632. Min Act: -0.1700
Data Index: 2238996 (Open Web Text)
Max Activating Token Index: 704
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2320. Min Act: -0.1700
Data Index: 8325212 (Open Web Text)
Max Activating Token Index: 532
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2320. Min Act: -0.1700
Data Index: 1325285 (Open Web Text)
Max Activating Token Index: 769
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2320. Min Act: -0.1700
Data Index: 361472 (Open Web Text)
Max Activating Token Index: 230
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2320. Min Act: -0.1700
Data Index: 4247078 (Open Web Text)
Max Activating Token Index: 192
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.1695. Min Act: -0.1700
Data Index: 8332208 (Open Web Text)
Max Activating Token Index: 406
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.1695. Min Act: -0.1700
Data Index: 6565629 (Open Web Text)
Max Activating Token Index: 674
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.2007. Min Act: -0.1700
Data Index: 149748 (Open Web Text)
Max Activating Token Index: 282
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.1695. Min Act: -0.1700
Data Index: 3102660 (Open Web Text)
Max Activating Token Index: 356
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 6.7320. Min Range: -6.7320
Max Act: 6.1382. Min Act: -0.1700
Data Index: 2670636 (Open Web Text)
Max Activating Token Index: 342
Click toggle to see full text
Truncated
Full Text #19