Model: GPT-2 Xl: 48 Layers, 6400 Neurons per Layer
Dataset: Open Web Text
Neuron 5054 in Layer 41
Transformer Lens Loading: HookedTransformer.from_pretrained('gpt2-xl')
Text #0
Max Range: 9.1878. Min Range: -9.1878
Max Act: 9.1878. Min Act: -0.1700
Data Index: 4757134 (Open Web Text)
Max Activating Token Index: 204
Click toggle to see full text
Truncated
Full Text #0
Text #1
Max Range: 9.1878. Min Range: -9.1878
Max Act: 9.1878. Min Act: -0.1700
Data Index: 608375 (Open Web Text)
Max Activating Token Index: 652
Click toggle to see full text
Truncated
Full Text #1
Text #2
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.8128. Min Act: -0.1700
Data Index: 3706870 (Open Web Text)
Max Activating Token Index: 475
Click toggle to see full text
Truncated
Full Text #2
Text #3
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.6253. Min Act: -0.1700
Data Index: 3689639 (Open Web Text)
Max Activating Token Index: 451
Click toggle to see full text
Truncated
Full Text #3
Text #4
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.5628. Min Act: -0.1700
Data Index: 2484270 (Open Web Text)
Max Activating Token Index: 337
Click toggle to see full text
Truncated
Full Text #4
Text #5
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.5628. Min Act: -0.1700
Data Index: 5294822 (Open Web Text)
Max Activating Token Index: 968
Click toggle to see full text
Truncated
Full Text #5
Text #6
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.2503. Min Act: -0.1700
Data Index: 6342150 (Open Web Text)
Max Activating Token Index: 584
Click toggle to see full text
Truncated
Full Text #6
Text #7
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.3128. Min Act: -0.1700
Data Index: 2389894 (Open Web Text)
Max Activating Token Index: 343
Click toggle to see full text
Truncated
Full Text #7
Text #8
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.2503. Min Act: -0.1700
Data Index: 6077563 (Open Web Text)
Max Activating Token Index: 328
Click toggle to see full text
Truncated
Full Text #8
Text #9
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.2503. Min Act: -0.1700
Data Index: 511991 (Open Web Text)
Max Activating Token Index: 470
Click toggle to see full text
Truncated
Full Text #9
Text #10
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.1878. Min Act: -0.1700
Data Index: 1715899 (Open Web Text)
Max Activating Token Index: 768
Click toggle to see full text
Truncated
Full Text #10
Text #11
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.1878. Min Act: -0.1700
Data Index: 897496 (Open Web Text)
Max Activating Token Index: 497
Click toggle to see full text
Truncated
Full Text #11
Text #12
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.1253. Min Act: -0.1700
Data Index: 2970836 (Open Web Text)
Max Activating Token Index: 883
Click toggle to see full text
Truncated
Full Text #12
Text #13
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.0003. Min Act: -0.1700
Data Index: 2729750 (Open Web Text)
Max Activating Token Index: 848
Click toggle to see full text
Truncated
Full Text #13
Text #14
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.0628. Min Act: -0.1700
Data Index: 4296654 (Open Web Text)
Max Activating Token Index: 429
Click toggle to see full text
Truncated
Full Text #14
Text #15
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.0628. Min Act: -0.1700
Data Index: 146269 (Open Web Text)
Max Activating Token Index: 1015
Click toggle to see full text
Truncated
Full Text #15
Text #16
Max Range: 9.1878. Min Range: -9.1878
Max Act: 7.9378. Min Act: -0.1700
Data Index: 1248064 (Open Web Text)
Max Activating Token Index: 688
Click toggle to see full text
Truncated
Full Text #16
Text #17
Max Range: 9.1878. Min Range: -9.1878
Max Act: 8.0003. Min Act: -0.1700
Data Index: 6017903 (Open Web Text)
Max Activating Token Index: 930
Click toggle to see full text
Truncated
Full Text #17
Text #18
Max Range: 9.1878. Min Range: -9.1878
Max Act: 7.9378. Min Act: -0.1700
Data Index: 3947172 (Open Web Text)
Max Activating Token Index: 508
Click toggle to see full text
Truncated
Full Text #18
Text #19
Max Range: 9.1878. Min Range: -9.1878
Max Act: 7.9378. Min Act: -0.1700
Data Index: 5127226 (Open Web Text)
Max Activating Token Index: 136
Click toggle to see full text
Truncated
Full Text #19