Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 2525 in Layer 32
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.8245. Min Act: -0.1700
Data Index: 7800518 (Open Web Text)
Max Activating Token Index: 774
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.7620. Min Act: -0.1700
Data Index: 2171717 (Open Web Text)
Max Activating Token Index: 834
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.6995. Min Act: -0.1700
Data Index: 1241259 (Open Web Text)
Max Activating Token Index: 641
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.6370. Min Act: -0.1700
Data Index: 1515007 (Open Web Text)
Max Activating Token Index: 460
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.5745. Min Act: -0.1700
Data Index: 5555574 (Open Web Text)
Max Activating Token Index: 395
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.5745. Min Act: -0.1700
Data Index: 6585496 (Open Web Text)
Max Activating Token Index: 492
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.5120. Min Act: -0.1700
Data Index: 2827015 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.4807. Min Act: -0.1700
Data Index: 8808678 (Open Web Text)
Max Activating Token Index: 687
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.5120. Min Act: -0.1700
Data Index: 7106306 (Open Web Text)
Max Activating Token Index: 412
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.4807. Min Act: -0.1700
Data Index: 7172047 (Open Web Text)
Max Activating Token Index: 901
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.4182. Min Act: -0.1700
Data Index: 3161780 (Open Web Text)
Max Activating Token Index: 909
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.4182. Min Act: -0.1700
Data Index: 5197327 (Open Web Text)
Max Activating Token Index: 238
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.3245. Min Act: -0.1700
Data Index: 8134217 (Open Web Text)
Max Activating Token Index: 815
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2932. Min Act: -0.1700
Data Index: 461961 (Open Web Text)
Max Activating Token Index: 833
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2932. Min Act: -0.1700
Data Index: 2253058 (Open Web Text)
Max Activating Token Index: 773
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2932. Min Act: -0.1700
Data Index: 1140271 (Open Web Text)
Max Activating Token Index: 341
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2307. Min Act: -0.1700
Data Index: 2899783 (Open Web Text)
Max Activating Token Index: 764
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2307. Min Act: -0.1700
Data Index: 5179197 (Open Web Text)
Max Activating Token Index: 678
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2620. Min Act: -0.1700
Data Index: 7119288 (Open Web Text)
Max Activating Token Index: 389
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 7.8245. Min Range: -7.8245
Max Act: 7.2620. Min Act: -0.1700
Data Index: 251228 (Open Web Text)
Max Activating Token Index: 529
Click toggle to see full text
Truncated
Full Text #19