Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2201 in Layer 10
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.7245. Min Act: -0.1700
Data Index: 3121668 (Open Web Text)
Max Activating Token Index: 481
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.7245. Min Act: -0.1700
Data Index: 386021 (Open Web Text)
Max Activating Token Index: 613
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6933. Min Act: -0.1700
Data Index: 2989696 (Open Web Text)
Max Activating Token Index: 643
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6933. Min Act: -0.1700
Data Index: 2511700 (Open Web Text)
Max Activating Token Index: 804
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6933. Min Act: -0.1700
Data Index: 6998368 (Open Web Text)
Max Activating Token Index: 458
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.7245. Min Act: -0.1700
Data Index: 3791658 (Open Web Text)
Max Activating Token Index: 64
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6620. Min Act: -0.1700
Data Index: 4762730 (Open Web Text)
Max Activating Token Index: 752
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6308. Min Act: -0.1700
Data Index: 2320182 (Open Web Text)
Max Activating Token Index: 863
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6308. Min Act: -0.1700
Data Index: 1673223 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6308. Min Act: -0.1700
Data Index: 5120326 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6308. Min Act: -0.1700
Data Index: 8674199 (Open Web Text)
Max Activating Token Index: 890
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6308. Min Act: -0.1700
Data Index: 2060844 (Open Web Text)
Max Activating Token Index: 585
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.6308. Min Act: -0.1700
Data Index: 2971494 (Open Web Text)
Max Activating Token Index: 331
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5683. Min Act: -0.1700
Data Index: 376770 (Open Web Text)
Max Activating Token Index: 574
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5995. Min Act: -0.1700
Data Index: 6317470 (Open Web Text)
Max Activating Token Index: 798
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5995. Min Act: -0.1700
Data Index: 398417 (Open Web Text)
Max Activating Token Index: 382
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5995. Min Act: -0.1700
Data Index: 1962930 (Open Web Text)
Max Activating Token Index: 493
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5683. Min Act: -0.1700
Data Index: 4843768 (Open Web Text)
Max Activating Token Index: 257
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5683. Min Act: -0.1700
Data Index: 1355575 (Open Web Text)
Max Activating Token Index: 571
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 4.7245. Min Range: -4.7245
Max Act: 4.5683. Min Act: -0.1700
Data Index: 4776435 (Open Web Text)
Max Activating Token Index: 302
Click toggle to see full text
Truncated
Full Text #19